no code implementations • ECCV 2020 • Ruizheng Wu, Xin Tao, Ying-Cong Chen, Xiaoyong Shen, Jiaya Jia
Unpaired image-to-image translation aims to translate images from the source class to target one by providing sufficient data for these classes.
no code implementations • ECCV 2020 • Ruizheng Wu, Huaijia Lin, Xiaojuan Qi, Jiaya Jia
Video propagation is a fundamental problem in video processing where guidance frame predictions are propagated to guide predictions of the target frame.
no code implementations • ECCV 2020 • Zetong Yang, Yanan sun, Shu Liu, Xiaojuan Qi, Jiaya Jia
In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level.
2 code implementations • 11 Apr 2024 • Bohao Peng, Zhuotao Tian, Shu Liu, MingChang Yang, Jiaya Jia
In this study, we introduce the Scalable Language Model (SLM) to overcome these limitations within a more challenging and generalized setting, representing a significant advancement toward practical applications for continual learning.
no code implementations • 10 Apr 2024 • Senqiao Yang, Zhuotao Tian, Li Jiang, Jiaya Jia
This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge.
2 code implementations • 27 Mar 2024 • Yanwei Li, Yuechen Zhang, Chengyao Wang, Zhisheng Zhong, Yixin Chen, Ruihang Chu, Shaoteng Liu, Jiaya Jia
We try to narrow the gap by mining the potential of VLMs for better performance and any-to-any workflow from three aspects, i. e., high-resolution visual tokens, high-quality data, and VLM-guided generation.
Ranked #9 on Visual Question Answering on MM-Vet
1 code implementation • 21 Mar 2024 • Bohao Peng, Xiaoyang Wu, Li Jiang, Yukang Chen, Hengshuang Zhao, Zhuotao Tian, Jiaya Jia
This exploration led to the creation of Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a lightweight module to greatly enhance the adaptivity of sparse CNNs at minimal computational cost.
Ranked #5 on 3D Semantic Segmentation on SemanticKITTI (val mIoU metric)
1 code implementation • 14 Mar 2024 • Chengyao Wang, Li Jiang, Xiaoyang Wu, Zhuotao Tian, Bohao Peng, Hengshuang Zhao, Jiaya Jia
To address this issue, we propose GroupContrast, a novel approach that combines segment grouping and semantic-aware contrastive learning.
no code implementations • 29 Feb 2024 • Shaoteng Liu, Haoqi Yuan, Minda Hu, Yanwei Li, Yukang Chen, Shu Liu, Zongqing Lu, Jiaya Jia
To seamlessly integrate both modalities, we introduce a two-level hierarchical framework, RL-GPT, comprising a slow agent and a fast agent.
no code implementations • 22 Feb 2024 • Jingyao Li, Pengguang Chen, Xuan Ju, Hong Xu, Jiaya Jia
Our research aims to bridge the domain gap between natural and artificial scenarios with efficient tuning strategies.
no code implementations • 5 Jan 2024 • Jingyao Li, Pengguang Chen, Shaozuo Yu, Shu Liu, Jiaya Jia
The crux of effective out-of-distribution (OOD) detection lies in acquiring a robust in-distribution (ID) representation, distinct from OOD samples.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
2 code implementations • 28 Dec 2023 • Zhongshen Zeng, Pengguang Chen, Shu Liu, Haiyun Jiang, Jiaya Jia
In this work, we introduce a novel evaluation paradigm for Large Language Models, one that challenges them to engage in meta-reasoning.
no code implementations • 28 Dec 2023 • Senqiao Yang, Tianyuan Qu, Xin Lai, Zhuotao Tian, Bohao Peng, Shu Liu, Jiaya Jia
While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish different instances of the target region, and constrained by the pre-defined textual response formats.
1 code implementation • 26 Dec 2023 • Jingyao Li, Pengguang Chen, Shaozuo Yu, Shu Liu, Jiaya Jia
Experimental results demonstrate that, when labeling 80% of the samples, the performance of the current SOTA method declines by 0. 74%, whereas our proposed BAL achieves performance comparable to the full dataset.
1 code implementation • 26 Dec 2023 • Jingyao Li, Pengguang Chen, Jiaya Jia
Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks.
Ranked #1 on Code Generation on CodeContests (Test Set pass@1 metric)
1 code implementation • 7 Dec 2023 • Yuechen Zhang, Shengju Qian, Bohao Peng, Shu Liu, Jiaya Jia
Without tuning on LLaVA-v1. 5, our method secured 70. 7 in the MMBench test and 1552. 5 in MME-perception.
2 code implementations • 28 Nov 2023 • Yanwei Li, Chengyao Wang, Jiaya Jia
Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens.
Ranked #6 on Zero-Shot Video Question Answer on ActivityNet-QA
Image Captioning Video-based Generative Performance Benchmarking +2
1 code implementation • 27 Nov 2023 • Bin Xia, Shiyin Wang, Yingfan Tao, Yitong Wang, Jiaya Jia
In the first stage, we train the MLLM to grasp the properties of image generation and editing, enabling it to generate detailed prompts.
no code implementations • 8 Oct 2023 • Yixin Chen, Shuai Zhang, Boran Han, Jiaya Jia
In-context learning (ICL) involves reasoning from given contextual examples.
2 code implementations • 21 Sep 2023 • Yukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han, Jiaya Jia
For example, training on the context length of 8192 needs 16x computational costs in self-attention layers as that of 2048.
1 code implementation • ICCV 2023 • Xin Lai, Yuhui Yuan, Ruihang Chu, Yukang Chen, Han Hu, Jiaya Jia
Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead.
1 code implementation • 8 Aug 2023 • Yilun Chen, Zhiding Yu, Yukang Chen, Shiyi Lan, Animashree Anandkumar, Jiaya Jia, Jose Alvarez
For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall.
Ranked #8 on 3D Object Detection on nuScenes
2 code implementations • 1 Aug 2023 • Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li, Yuhui Yuan, Shu Liu, Jiaya Jia
In this work, we propose a new segmentation task -- reasoning segmentation.
no code implementations • 27 Jun 2023 • Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chengyao Wang, Shu Liu, Jingyong Su, Jiaya Jia
We hope our work can benefit broader industrial applications where novel classes with limited annotations are required to be decently identified.
2 code implementations • NeurIPS 2023 • Yuechen Zhang, Jinbo Xing, Eric Lo, Jiaya Jia
Our pipeline enhances the generation quality of image variations by aligning the image generation process to the source image's inversion chain.
no code implementations • 22 Apr 2023 • Shaoteng Liu, Xiangyu Zhang, Tao Hu, Jiaya Jia
In each iteration, the input to VSA is one view (or multiple views) of a 3D object and the output is a synthesized image in another target pose.
no code implementations • 15 Apr 2023 • Jingyao Li, Pengguang Chen, Shengju Qian, Jiaya Jia
However, existing models easily misidentify input pixels from unseen classes, thus confusing novel classes with semantically-similar ones.
1 code implementation • CVPR 2023 • Tao Hu, Xiaogang Xu, Ruihang Chu, Jiaya Jia
However, artifacts still appear in rendered images, due to the challenges in extracting continuous and discriminative 3D features from point clouds.
no code implementations • CVPR 2023 • Tao Hu, Xiaogang Xu, Shu Liu, Jiaya Jia
Also, we present Point Encoding to build Multi-scale Radiance Fields that provide discriminative 3D point features.
1 code implementation • CVPR 2023 • Bohao Peng, Zhuotao Tian, Xiaoyang Wu, Chenyao Wang, Shu Liu, Jingyong Su, Jiaya Jia
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations.
Ranked #7 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
2 code implementations • CVPR 2023 • Xin Lai, Yukang Chen, Fanbin Lu, Jianhui Liu, Jiaya Jia
In this work, we study the varying-sparsity distribution of LiDAR points and present SphereFormer to directly aggregate information from dense close points to the sparse distant ones.
Ranked #1 on Semantic Segmentation on KITTI Semantic Segmentation
2 code implementations • 21 Mar 2023 • Zhuotao Tian, Jiequan Cui, Li Jiang, Xiaojuan Qi, Xin Lai, Yixin Chen, Shu Liu, Jiaya Jia
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing.
2 code implementations • CVPR 2023 • Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia
Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies.
Ranked #1 on 3D Object Detection on Argoverse2
1 code implementation • 8 Mar 2023 • Shaoteng Liu, Yuechen Zhang, Wenbo Li, Zhe Lin, Jiaya Jia
This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control.
no code implementations • 1 Mar 2023 • Shengju Qian, Huiwen Chang, Yuanzhen Li, Zizhao Zhang, Jiaya Jia, Han Zhang
We propose Stratified Image Transformer(StraIT), a pure non-autoregressive(NAR) generative model that demonstrates superiority in high-quality image synthesis over existing autoregressive(AR) and diffusion models(DMs).
1 code implementation • CVPR 2023 • Jingyao Li, Pengguang Chen, Shaozuo Yu, Zexin He, Shu Liu, Jiaya Jia
The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples.
Ranked #12 on Out-of-Distribution Detection on ImageNet-1k vs Places (AUROC metric)
2 code implementations • CVPR 2023 • Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia
Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers.
no code implementations • ICCV 2023 • Fanbin Lu, Xufeng Yao, Chi-Wing Fu, Jiaya Jia
Our denoising model outperforms the state-of-the-art reconstruction-based anomaly detection methods for precise anomaly localization and high-quality normal image reconstruction on the MVTec-AD benchmark.
1 code implementation • ICCV 2023 • Yilun Chen, Zhiding Yu, Yukang Chen, Shiyi Lan, Anima Anandkumar, Jiaya Jia, Jose M. Alvarez
For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall.
no code implementations • CVPR 2023 • Ruihang Chu, Zhengzhe Liu, Xiaoqing Ye, Xiao Tan, Xiaojuan Qi, Chi-Wing Fu, Jiaya Jia
The key of Cart is to utilize the prediction of object structures to connect visual observations with user commands for effective manipulations.
no code implementations • ICCV 2023 • Yanwei Li, Zhiding Yu, Jonah Philion, Anima Anandkumar, Sanja Fidler, Jiaya Jia, Jose Alvarez
In this work, we present an end-to-end framework for camera-based 3D multi-object tracking, called DQTrack.
no code implementations • ICCV 2023 • Lu Qi, Jason Kuen, Tiancheng Shen, Jiuxiang Gu, Wenbo Li, Weidong Guo, Jiaya Jia, Zhe Lin, Ming-Hsuan Yang
Given the high-quality and -resolution nature of the dataset, we propose CropFormer which is designed to tackle the intractability of instance-level segmentation on high-resolution images.
no code implementations • 21 Dec 2022 • Shengju Qian, Yi Zhu, Wenbo Li, Mu Li, Jiaya Jia
The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm.
no code implementations • 11 Dec 2022 • Xiaogang Xu, Hengshuang Zhao, Philip Torr, Jiaya Jia
In this paper, we use Deep Generative Networks (DGNs) with a novel training mechanism to eliminate the distribution gap.
1 code implementation • CVPR 2023 • Yuechen Zhang, Zexin He, Jinbo Xing, Xufeng Yao, Jiaya Jia
We propose a ray registration process based on the stylized reference view to obtain pseudo-ray supervision in novel views.
2 code implementations • 6 Dec 2022 • Wenbo Li, Xin Yu, Kun Zhou, Yibing Song, Zhe Lin, Jiaya Jia
To achieve high-quality results with low computational cost, we present a novel pixel spread model (PSM) that iteratively employs decoupled probabilistic modeling, combining the optimization efficiency of GANs with the prediction tractability of probabilistic models.
1 code implementation • 10 Nov 2022 • Lu Qi, Jason Kuen, Weidong Guo, Tiancheng Shen, Jiuxiang Gu, Jiaya Jia, Zhe Lin, Ming-Hsuan Yang
It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image.
4 code implementations • 26 Sep 2022 • Jiequan Cui, Zhisheng Zhong, Zhuotao Tian, Shu Liu, Bei Yu, Jiaya Jia
Based on theoretical analysis, we observe that supervised contrastive loss tends to bias high-frequency classes and thus increases the difficulty of imbalanced learning.
Ranked #7 on Long-tail Learning on iNaturalist 2018
no code implementations • 29 Jul 2022 • Zelin Zhao, Jiaya Jia
On the one hand, NeRFA considers the volumetric rendering equation as a soft feature modulation procedure.
1 code implementation • 20 Jul 2022 • Xin Lai, Zhuotao Tian, Xiaogang Xu, Yingcong Chen, Shu Liu, Hengshuang Zhao, LiWei Wang, Jiaya Jia
Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations.
1 code implementation • 12 Jul 2022 • Zelin Zhao, Ze Wu, Yueqing Zhuang, Boxun Li, Jiaya Jia
During inference, a pixel-wise association procedure is proposed to recover object connections through frames based on the pixel-wise prediction.
1 code implementation • 5 Jul 2022 • Xiaogang Xu, RuiXing Wang, Chi-Wing Fu, Jiaya Jia
Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy.
no code implementations • 4 Jul 2022 • Xiaogang Xu, Yitong Yu, Nianjuan Jiang, Jiangbo Lu, Bei Yu, Jiaya Jia
Moreover, we also propose a new video denoising framework, called Recurrent Video Denoising Transformer (RVDT), which can achieve SOTA performance on PVDD and other current video denoising benchmarks.
2 code implementations • CVPR 2023 • Yukang Chen, Jianhui Liu, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia
Recent advance in 2D CNNs has revealed that large kernels are important.
1 code implementation • 2 Jun 2022 • Tao Hu, Shu Liu, Yilun Chen, Tiancheng Shen, Jiaya Jia
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes.
1 code implementation • 1 Jun 2022 • Yanwei Li, Yilun Chen, Xiaojuan Qi, Zeming Li, Jian Sun, Jiaya Jia
To this end, the modality-specific space is first designed to represent different inputs in the voxel feature space.
1 code implementation • CVPR 2022 • Yanwei Li, Xiaojuan Qi, Yukang Chen, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia
In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion.
1 code implementation • CVPR 2022 • Liying Lu, Ruizheng Wu, Huaijia Lin, Jiangbo Lu, Jiaya Jia
Video frame interpolation (VFI), which aims to synthesize intermediate frames of a video, has made remarkable progress with development of deep convolutional networks over past years.
Ranked #5 on Video Frame Interpolation on MSU Video Frame Interpolation (VMAF metric)
2 code implementations • CVPR 2022 • Yukang Chen, Yanwei Li, Xiangyu Zhang, Jian Sun, Jiaya Jia
In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction.
1 code implementation • 6 Apr 2022 • Yilun Chen, Shijia Huang, Shu Liu, Bei Yu, Jiaya Jia
First, to effectively lift the 2D information to stereo volume, we propose depth-wise plane sweeping (DPS) that allows denser connections and extracts depth-guided features.
5 code implementations • 5 Apr 2022 • Jiequan Cui, Yuhui Yuan, Zhisheng Zhong, Zhuotao Tian, Han Hu, Stephen Lin, Jiaya Jia
In this paper, we study the problem of class imbalance in semantic segmentation.
Ranked #21 on Semantic Segmentation on ADE20K
1 code implementation • CVPR 2022 • Shijia Huang, Yilun Chen, Jiaya Jia, LiWei Wang
The multi-view space enables the network to learn a more robust multi-modal representation for 3D visual grounding and eliminates the dependence on specific views.
1 code implementation • CVPR 2022 • Wenbo Li, Zhe Lin, Kun Zhou, Lu Qi, Yi Wang, Jiaya Jia
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem.
Ranked #1 on Image Inpainting on CelebA-HQ
4 code implementations • CVPR 2022 • Xin Lai, Jianhui Liu, Li Jiang, LiWei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia
In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance.
Ranked #15 on Semantic Segmentation on ScanNet
2 code implementations • 22 Mar 2022 • Zhisheng Zhong, Jiequan Cui, Zeming Li, Eric Lo, Jian Sun, Jiaya Jia
Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognition.
Ranked #5 on Long-tail Learning on CIFAR-10-LT (ρ=10)
1 code implementation • CVPR 2022 • Zetong Yang, Li Jiang, Yanan sun, Bernt Schiele, Jiaya Jia
This is achieved by introducing an intermediate representation, i. e., Q-representation, in the querying stage to serve as a bridge between the embedding stage and task heads.
Ranked #7 on Semantic Segmentation on S3DIS
no code implementations • 2 Mar 2022 • Yixin Chen, Zhuotao Tian, Pengguang Chen, Shu Liu, Jiaya Jia
We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them.
no code implementations • CVPR 2022 • Ruihang Chu, Xiaoqing Ye, Zhengzhe Liu, Xiao Tan, Xiaojuan Qi, Chi-Wing Fu, Jiaya Jia
We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation.
no code implementations • CVPR 2022 • Tao Hu, Shu Liu, Yilun Chen, Tiancheng Shen, Jiaya Jia
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes.
1 code implementation • CVPR 2022 • Xiaogang Xu, RuiXing Wang, Chi-Wing Fu, Jiaya Jia
They are long-range operations for image regions of extremely low Signal-to-Noise-Ratio (SNR) and short-range operations for other regions.
Ranked #2 on Low-Light Image Enhancement on LIME
1 code implementation • 19 Dec 2021 • Wenbo Li, Xin Lu, Shengju Qian, Jiangbo Lu, Xiangyu Zhang, Jiaya Jia
Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems.
Ranked #5 on Image Super-Resolution on Set5 - 2x upscaling (using extra training data)
1 code implementation • 9 Dec 2021 • Lu Qi, Jason Kuen, Zhe Lin, Jiuxiang Gu, Fengyun Rao, Dian Li, Weidong Guo, Zhen Wen, Ming-Hsuan Yang, Jiaya Jia
To improve instance-level detection/segmentation performance, existing self-supervised and semi-supervised methods extract either task-unrelated or task-specific training signals from unlabeled data.
1 code implementation • CVPR 2022 • Tiancheng Shen, Yuechen Zhang, Lu Qi, Jason Kuen, Xingyu Xie, Jianlong Wu, Zhe Lin, Jiaya Jia
To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation.
no code implementations • NeurIPS 2021 • Shengju Qian, Hao Shao, Yi Zhu, Mu Li, Jiaya Jia
In this work, we analyze the uncharted problem of aliasing in vision transformer and explore to incorporate anti-aliasing properties.
1 code implementation • ICCV 2021 • Li Jiang, Shaoshuai Shi, Zhuotao Tian, Xin Lai, Shu Liu, Chi-Wing Fu, Jiaya Jia
To address the high cost and challenges of 3D point-level labeling, we present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance.
1 code implementation • 28 Sep 2021 • Xiaoliu Luo, Zhuotao Tian, Taiping Zhang, Bei Yu, Yuan Yan Tang, Jiaya Jia
In this work, we revisit the prior mask guidance proposed in ``Prior Guided Feature Enrichment Network for Few-Shot Segmentation''.
1 code implementation • ICCV 2021 • Yixin Chen, Pengguang Chen, Shu Liu, LiWei Wang, Jiaya Jia
Effectively structuring deep knowledge plays a pivotal role in transfer from teacher to student, especially in semantic vision tasks.
no code implementations • ICCV 2021 • Yi Wang, Lu Qi, Ying-Cong Chen, Xiangyu Zhang, Jiaya Jia
In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts.
2 code implementations • CVPR 2021 • Lu Qi, Jason Kuen, Jiuxiang Gu, Zhe Lin, Yi Wang, Yukang Chen, Yanwei Li, Jiaya Jia
However, this option traditionally hurts the detection performance much.
no code implementations • 30 Aug 2021 • Pengguang Chen, Yixin Chen, Shu Liu, MingChang Yang, Jiaya Jia
We analyze the reason behind this phenomenon, and propose a novel irregular patch embedding module and adaptive patch fusion module to improve the performance.
1 code implementation • 17 Aug 2021 • Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia
In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.
no code implementations • 12 Aug 2021 • Xiaogang Xu, Yi Wang, LiWei Wang, Bei Yu, Jiaya Jia
To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video.
2 code implementations • 29 Jul 2021 • Lu Qi, Jason Kuen, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Zhe Lin, Philip Torr, Jiaya Jia
By removing the need of class label prediction, the models trained for such task can focus more on improving segmentation quality.
5 code implementations • ICCV 2021 • Jiequan Cui, Zhisheng Zhong, Shu Liu, Bei Yu, Jiaya Jia
In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition.
Ranked #14 on Long-tail Learning on iNaturalist 2018
2 code implementations • CVPR 2021 • Xin Lai, Zhuotao Tian, Li Jiang, Shu Liu, Hengshuang Zhao, LiWei Wang, Jiaya Jia
Semantic segmentation has made tremendous progress in recent years.
no code implementations • CVPR 2021 • Tao Hu, LiWei Wang, Xiaogang Xu, Shu Liu, Jiaya Jia
Recent single-view 3D reconstruction methods reconstruct object's shape and texture from a single image with only 2D image-level annotation.
1 code implementation • CVPR 2021 • Liying Lu, Wenbo Li, Xin Tao, Jiangbo Lu, Jiaya Jia
Therefore, high-quality correspondence matching is critical.
2 code implementations • NeurIPS 2020 • Wenbo Li, Kun Zhou, Lu Qi, Nianjuan Jiang, Jiangbo Lu, Jiaya Jia
Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version.
7 code implementations • CVPR 2021 • Pengguang Chen, Shu Liu, Hengshuang Zhao, Jiaya Jia
Knowledge distillation transfers knowledge from the teacher network to the student one, with the goal of greatly improving the performance of the student network.
Ranked #12 on Knowledge Distillation on CIFAR-100
5 code implementations • CVPR 2021 • Zhisheng Zhong, Jiequan Cui, Shu Liu, Jiaya Jia
Motivated by the fact that predicted probability distributions of classes are highly related to the numbers of class instances, we propose label-aware smoothing to deal with different degrees of over-confidence for classes and improve classifier learning.
Ranked #16 on Long-tail Learning on CIFAR-10-LT (ρ=100)
1 code implementation • CVPR 2021 • Pengguang Chen, Shu Liu, Jiaya Jia
It is even comparable to the contrastive learning methods when only half of training batches are used.
1 code implementation • CVPR 2021 • Yukang Chen, Yanwei Li, Tao Kong, Lu Qi, Ruihang Chu, Lei LI, Jiaya Jia
We propose Scale-aware AutoAug to learn data augmentation policies for object detection.
2 code implementations • 29 Mar 2021 • Wenbo Li, Kun Zhou, Lu Qi, Liying Lu, Nianjuan Jiang, Jiangbo Lu, Jiaya Jia
We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input.
1 code implementation • CVPR 2021 • WenBo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong
Via the \emph{BPM}, complementary 2D and 3D information can interact with each other in multiple architectural levels, such that advantages in these two visual domains can be combined for better scene recognition.
Ranked #11 on Semantic Segmentation on ScanNet
1 code implementation • ICCV 2021 • Huaijia Lin, Ruizheng Wu, Shu Liu, Jiangbo Lu, Jiaya Jia
Video instance segmentation (VIS) aims to segment and associate all instances of predefined classes for each frame in videos.
Ranked #2 on Unsupervised Video Object Segmentation on DAVIS 2017 (val) (using extra training data)
5 code implementations • 26 Jan 2021 • Jiequan Cui, Shu Liu, Zhuotao Tian, Zhisheng Zhong, Jiaya Jia
From this perspective, the trivial solution utilizes different branches for the head, medium, and tail classes respectively, and then sums their outputs as the final results is not feasible.
Ranked #22 on Long-tail Learning on CIFAR-10-LT (ρ=10)
no code implementations • 1 Jan 2021 • Xiaogang Xu, Hengshuang Zhao, Philip Torr, Jiaya Jia
Specifically, compared with previous methods, we propose a more efficient pixel-level training constraint to weaken the hardness of aligning adversarial samples to clean samples, which can thus obviously enhance the robustness on adversarial samples.
1 code implementation • ICCV 2021 • RuiXing Wang, Xiaogang Xu, Chi-Wing Fu, Jiangbo Lu, Bei Yu, Jiaya Jia
Low-light video enhancement is an important task.
24 code implementations • ICCV 2021 • Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun
For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70. 4% on Area 5, outperforming the strongest prior model by 3. 3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
Ranked #3 on 3D Semantic Segmentation on STPLS3D
2 code implementations • 13 Dec 2020 • Xiaojuan Qi, Zhengzhe Liu, Renjie Liao, Philip H. S. Torr, Raquel Urtasun, Jiaya Jia
Note that GeoNet++ is generic and can be used in other depth/normal prediction frameworks to improve the quality of 3D reconstruction and pixel-wise accuracy of depth and surface normals.
6 code implementations • CVPR 2021 • Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia
In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN.
Ranked #1 on Panoptic Segmentation on COCO minival (SQ metric)
3 code implementations • ICCV 2021 • Jiequan Cui, Shu Liu, LiWei Wang, Jiaya Jia
Previous adversarial training raises model robustness under the compromise of accuracy on natural data.
Ranked #1 on Adversarial Defense on CIFAR-100
1 code implementation • CVPR 2022 • Zhuotao Tian, Xin Lai, Li Jiang, Shu Liu, Michelle Shu, Hengshuang Zhao, Jiaya Jia
Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image.
3 code implementations • 4 Aug 2020 • Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Zhicheng Yang, Ruiyu Li, Jiaya Jia
It consists of novel designs of (1) a training-free prior mask generation method that not only retains generalization power but also improves model performance and (2) Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks.
Ranked #67 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
1 code implementation • ECCV 2020 • Wenbo Li, Xin Tao, Taian Guo, Lu Qi, Jiangbo Lu, Jiaya Jia
Motivated by these findings, we propose a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-correspondence aggregation scheme to explore self-similarity of images across scales.
1 code implementation • CVPR 2020 • Hengshuang Zhao, Jiaya Jia, Vladlen Koltun
Recent work has shown that self-attention can serve as a basic building block for image recognition models.
4 code implementations • 26 Apr 2020 • Yukang Chen, Peizhen Zhang, Zeming Li, Yanwei Li, Xiangyu Zhang, Lu Qi, Jian Sun, Jiaya Jia
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.
1 code implementation • CVPR 2020 • Yi Wang, Ying-Cong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia
Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.
2 code implementations • CVPR 2020 • Li Jiang, Hengshuang Zhao, Shaoshuai Shi, Shu Liu, Chi-Wing Fu, Jiaya Jia
Instance segmentation is an important task for scene understanding.
Ranked #5 on 3D Instance Segmentation on STPLS3D
2 code implementations • ECCV 2020 • Yi Wang, Ying-Cong Chen, Xin Tao, Jiaya Jia
Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image.
1 code implementation • ICCV 2021 • Xiaogang Xu, Hengshuang Zhao, Jiaya Jia
Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations, especially on the classification task.
no code implementations • 13 Mar 2020 • Lu Qi, Yi Wang, Yukang Chen, Yingcong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia
In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.
2 code implementations • CVPR 2020 • Zetong Yang, Yanan sun, Shu Liu, Jiaya Jia
Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods.
7 code implementations • 13 Jan 2020 • Pengguang Chen, Shu Liu, Hengshuang Zhao, Xingquan Wang, Jiaya Jia
Then we show limitation of existing information dropping algorithms and propose our structured method, which is simple and yet very effective.
1 code implementation • CVPR 2020 • Yilun Chen, Shu Liu, Xiaoyong Shen, Jiaya Jia
Most state-of-the-art 3D object detectors heavily rely on LiDAR sensors because there is a large performance gap between image-based and LiDAR-based methods.
no code implementations • ICCV 2019 • Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia
To incorporate point features in the edge branch, we establish a hierarchical graph framework, where the graph is initialized from a coarse layer and gradually enriched along the point decoding process.
Ranked #41 on Semantic Segmentation on S3DIS Area5
1 code implementation • ICCV 2019 • Shengju Qian, Keqiang Sun, Wayne Wu, Chen Qian, Jiaya Jia
Facial landmark detection, or face alignment, is a fundamental task that has been extensively studied.
Ranked #18 on Face Alignment on WFLW
no code implementations • ICCV 2019 • Yilun Chen, Shu Liu, Xiaoyong Shen, Jiaya Jia
We present a unified, efficient and effective framework for point-cloud based 3D object detection.
no code implementations • ICCV 2019 • Zetong Yang, Yanan sun, Shu Liu, Xiaoyong Shen, Jiaya Jia
We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD).
1 code implementation • ICCV 2019 • Ruizheng Wu, Xin Tao, Xiaodong Gu, Xiaoyong Shen, Jiaya Jia
Current image translation methods, albeit effective to produce high-quality results in various applications, still do not consider much geometric transform.
no code implementations • 2 Jul 2019 • Ruizheng Wu, Xiaodong Gu, Xin Tao, Xiaoyong Shen, Yu-Wing Tai, Jiaya Jia
In this paper, we are interested in generating an cartoon face of a person by using unpaired training data between real faces and cartoon ones.
no code implementations • 27 Jun 2019 • Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Jiaze Wang, Ruiyu Li, Xiaoyong Shen, Jiaya Jia
Albeit intensively studied, false prediction and unclear boundaries are still major issues of salient object detection.
3 code implementations • CVPR 2019 • Xinlong Wang, Shu Liu, Xiaoyong Shen, Chunhua Shen, Jiaya Jia
A 3D point cloud describes the real scene precisely and intuitively. To date how to segment diversified elements in such an informative 3D scene is rarely discussed.
Ranked #15 on 3D Instance Segmentation on S3DIS (mRec metric)
no code implementations • 7 Jan 2019 • Hong Zhang, Hao Ouyang, Shu Liu, Xiaojuan Qi, Xiaoyong Shen, Ruigang Yang, Jiaya Jia
With this principle, we present two conceptually simple and yet computational efficient modules, namely Cascade Prediction Fusion (CPF) and Pose Graph Neural Network (PGNN), to exploit underlying contextual information.
Ranked #10 on Pose Estimation on MPII Human Pose
no code implementations • 13 Dec 2018 • Zetong Yang, Yanan sun, Shu Liu, Xiaoyong Shen, Jiaya Jia
We present a novel 3D object detection framework, named IPOD, based on raw point cloud.
Ranked #1 on 3D Object Detection on KITTI Pedestrians Easy
no code implementations • NeurIPS 2018 • Lu Qi, Shu Liu, Jianping Shi, Jiaya Jia
Duplicate removal is a critical step to accomplish a reasonable amount of predictions in prevalent proposal-based object detection frameworks.
2 code implementations • NeurIPS 2018 • Yi Wang, Xin Tao, Xiaojuan Qi, Xiaoyong Shen, Jiaya Jia
In this paper, we propose a generative multi-column network for image inpainting.
4 code implementations • ECCV 2018 • Hengshuang Zhao, Yi Zhang, Shu Liu, Jianping Shi, Chen Change Loy, Dahua Lin, Jiaya Jia
We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes.
Ranked #51 on Semantic Segmentation on Cityscapes test
no code implementations • ECCV 2018 • Hengshuang Zhao, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Brian Price, Jiaya Jia
We present a new image search technique that, given a background image, returns compatible foreground objects for image compositing tasks.
no code implementations • ECCV 2018 • Li Jiang, Shaoshuai Shi, Xiaojuan Qi, Jiaya Jia
We propose to add geometric adversarial loss (GAL).
no code implementations • ECCV 2018 • Guorun Yang, Hengshuang Zhao, Jianping Shi, Zhidong Deng, Jiaya Jia
Disparity estimation for binocular stereo images finds a wide range of applications.
Ranked #6 on Semantic Segmentation on KITTI Semantic Segmentation
1 code implementation • CVPR 2018 • Ruiyu Li, Kaican Li, Yi-Chun Kuo, Michelle Shu, Xiaojuan Qi, Xiaoyong Shen, Jiaya Jia
We address the problem of image segmentation from natural language descriptions.
1 code implementation • CVPR 2018 • Xiaojuan Qi, Renjie Liao, Zhengzhe Liu, Raquel Urtasun, Jiaya Jia
In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image.
1 code implementation • CVPR 2018 • Xiaojuan Qi, Qifeng Chen, Jiaya Jia, Vladlen Koltun
We present a semi-parametric approach to photographic image synthesis from semantic layouts.
no code implementations • CVPR 2018 • Ying-Cong Chen, Huaijia Lin, Michelle Shu, Ruiyu Li, Xin Tao, Yangang Ye, Xiaoyong Shen, Jiaya Jia
Digital face manipulation has become a popular and fascinating way to touch images with the prevalence of smartphones and social networks.
10 code implementations • CVPR 2018 • Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, Jiaya Jia
The way that information propagates in neural networks is of great importance.
Ranked #3 on Object Detection on iSAID
4 code implementations • CVPR 2018 • Xin Tao, Hongyun Gao, Yi Wang, Xiaoyong Shen, Jue Wang, Jiaya Jia
In single image deblurring, the "coarse-to-fine" scheme, i. e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches.
Ranked #3 on Image Deblurring on GoPro (Params (M) metric, using extra training data)
no code implementations • ICCV 2017 • Chao Zhou, Hong Zhang, Xiaoyong Shen, Jiaya Jia
However, due to the limitations of these datasets and the difficulty of collecting new stereo data, current methods fail in real-life cases.
no code implementations • ICCV 2017 • Ying-Cong Chen, Xiaoyong Shen, Jiaya Jia
In this paper, we propose the task of restoring a portrait image from this process.
2 code implementations • ICCV 2017 • Xiaojuan Qi, Renjie Liao, Jiaya Jia, Sanja Fidler, Raquel Urtasun
Each node in the graph corresponds to a set of points and is associated with a hidden representation vector initialized with an appearance feature extracted by a unary CNN from 2D images.
Ranked #30 on Semantic Segmentation on SUN-RGBD (using extra training data)
no code implementations • ICCV 2017 • Shu Liu, Jiaya Jia, Sanja Fidler, Raquel Urtasun
By exploiting two-directional information, the second network groups horizontal and vertical lines into connected components.
1 code implementation • ICCV 2017 • Ruiyu Li, Makarand Tapaswi, Renjie Liao, Jiaya Jia, Raquel Urtasun, Sanja Fidler
We address the problem of recognizing situations in images.
Ranked #9 on Situation Recognition on imSitu
no code implementations • 28 Apr 2017 • Xiaoyong Shen, RuiXing Wang, Hengshuang Zhao, Jiaya Jia
A spatial-temporal refinement network is developed to further refine the segmentation errors in each frame and ensure temporal coherence in the segmentation map.
17 code implementations • ECCV 2018 • Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia
We focus on the challenging task of real-time semantic segmentation in this paper.
Ranked #11 on Dichotomous Image Segmentation on DIS-TE4
Dichotomous Image Segmentation Real-Time Semantic Segmentation +3
1 code implementation • ICCV 2017 • Xin Tao, Chao Zhou, Xiaoyong Shen, Jue Wang, Jiaya Jia
In this paper, we study an unconventional but practically meaningful reversibility problem of commonly used image filters.
1 code implementation • ICCV 2017 • Xin Tao, Hongyun Gao, Renjie Liao, Jue Wang, Jiaya Jia
In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results.
Ranked #11 on Video Super-Resolution on Vid4 - 4x upscaling
no code implementations • 7 Apr 2017 • Xiaoyong Shen, Ying-Cong Chen, Xin Tao, Jiaya Jia
We propose a principled convolutional neural pyramid (CNP) framework for general low-level vision and image processing tasks.
no code implementations • ICCV 2017 • Xiaoyong Shen, Hongyun Gao, Xin Tao, Chao Zhou, Jiaya Jia
Estimating correspondence between two images and extracting the foreground object are two challenges in computer vision.
67 code implementations • CVPR 2017 • Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
Ranked #4 on Video Semantic Segmentation on Cityscapes val
no code implementations • NeurIPS 2016 • Ruiyu Li, Jiaya Jia
Our method aims at reasoning over natural language questions and visual images.
no code implementations • CVPR 2016 • Shu Liu, Xiaojuan Qi, Jianping Shi, Hong Zhang, Jiaya Jia
Aiming at simultaneous detection and segmentation (SDS), we propose a proposal-free framework, which detect and segment object instances via mid-level patches.
no code implementations • CVPR 2016 • Di Lin, Jifeng Dai, Jiaya Jia, Kaiming He, Jian Sun
Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure.
no code implementations • 19 Jan 2016 • Tai-Pang Wu, Sai-Kit Yeung, Jiaya Jia, Chi-Keung Tang, Gerard Medioni
We prove a closed-form solution to tensor voting (CFTV): given a point set in any dimensions, our closed-form solution provides an exact, continuous and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation.
no code implementations • ICCV 2015 • Renjie Liao, Xin Tao, Ruiyu Li, Ziyang Ma, Jiaya Jia
We propose a new direction for fast video super-resolution (VideoSR) via a SR draft ensemble, which is defined as the set of high-resolution patch candidates before final image deconvolution.
no code implementations • ICCV 2015 • Xiaojuan Qi, Jianping Shi, Shu Liu, Renjie Liao, Jiaya Jia
In this paper, we propose an object clique potential for semantic segmentation.
no code implementations • ICCV 2015 • Shu Liu, Cewu Lu, Jiaya Jia
Regions-with-convolutional-neural-network (RCNN) is now a commonly employed object detection pipeline.
no code implementations • ICCV 2015 • Xiaoyong Shen, Chao Zhou, Li Xu, Jiaya Jia
Previous joint/guided filters directly transfer the structural information in the reference image to the target one.
no code implementations • ICCV 2015 • Cewu Lu, Shu Liu, Jiaya Jia, Chi-Keung Tang
Closed contour is an important objectness indicator.
3 code implementations • 27 Oct 2015 • Guofeng Zhang, Hao-Min Liu, Zilong Dong, Jiaya Jia, Tien-Tsin Wong, Hujun Bao
Our framework consists of steps of solving the feature `dropout' problem when indistinctive structures, noise or large image distortion exists, and of rapidly recognizing and joining common features located in different subsequences.
no code implementations • CVPR 2015 • Di Lin, Xiaoyong Shen, Cewu Lu, Jiaya Jia
Our major contribution is to propose a valve linkage function(VLF) for back-propagation chaining and form our deep localization, alignment and classification (LAC) system.
no code implementations • CVPR 2015 • Ziyang Ma, Renjie Liao, Xin Tao, Li Xu, Jiaya Jia, Enhua Wu
Ubiquitous motion blur easily fails multi-frame super-resolution (MFSR).
no code implementations • CVPR 2015 • Jianping Shi, Li Xu, Jiaya Jia
We tackle a fundamental problem to detect and estimate just noticeable blur (JNB) caused by defocus that spans a small number of pixels in images.
no code implementations • 10 May 2015 • Renjie Liao, Jianping Shi, Ziyang Ma, Jun Zhu, Jiaya Jia
Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering.
no code implementations • ICCV 2015 • Naiyan Wang, Jianping Shi, Dit-yan Yeung, Jiaya Jia
Surprisingly, our findings are discrepant with some common beliefs in the visual tracking research community.
no code implementations • NeurIPS 2014 • Li Xu, Jimmy SJ. Ren, Ce Liu, Jiaya Jia
Many fundamental image-related problems involve deconvolution operators.
Ranked #1 on Image Compression on FER2013
no code implementations • 11 Aug 2014 • Jianping Shi, Qiong Yan, Li Xu, Jiaya Jia
Complex structures commonly exist in natural images.
no code implementations • CVPR 2014 • Cewu Lu, Jiaya Jia, Chi-Keung Tang
We propose binary range-sample feature in depth.
no code implementations • CVPR 2014 • Shuai Yi, Xiaogang Wang, Cewu Lu, Jiaya Jia
We tackle stationary crowd analysis in this paper, which is similarly important as modeling mobile groups in crowd scenes and finds many applications in surveillance.
no code implementations • CVPR 2014 • Di Lin, Cewu Lu, Renjie Liao, Jiaya Jia
We address the false response influence problem when learning and applying discriminative parts to construct the mid-level representation in scene classification.
no code implementations • CVPR 2014 • Cewu Lu, Di Lin, Jiaya Jia, Chi-Keung Tang
Given a single outdoor image, this paper proposes a collaborative learning approach for labeling it as either sunny or cloudy.
no code implementations • CVPR 2014 • Jianping Shi, Li Xu, Jiaya Jia
Ubiquitous image blur brings out a practically important question what are effective features to differentiate between blurred and unblurred image regions.
no code implementations • CVPR 2014 • Qi Zhang, Li Xu, Jiaya Jia
Weighted median, in the form of either solver or filter, has been employed in a wide range of computer vision solutions for its beneficial properties in sparsity representation.
2D Semantic Segmentation task 1 (8 classes) Optical Flow Estimation +2
no code implementations • 19 May 2014 • Wei Feng, Jiaya Jia, Zhi-Qiang Liu
From our study, we make some reasonable recommendations of combining existing methods that perform the best in different situations for this challenging problem.
no code implementations • 13 Oct 2013 • Qiong Yan, Li Xu, Jiaya Jia
We propose a new model, together with advanced optimization, to separate a thick scattering media layer from a single natural image.
no code implementations • CVPR 2013 • Cewu Lu, Jiaping Shi, Jiaya Jia
Online dictionary learning is particularly useful for processing large-scale and dynamic data in computer vision.
no code implementations • CVPR 2013 • Qiong Yan, Li Xu, Jianping Shi, Jiaya Jia
When dealing with objects with complex structures, saliency detection confronts a critical problem namely that detection accuracy could be adversely affected if salient foreground or background in an image contains small-scale high-contrast patterns.
no code implementations • CVPR 2013 • Li Xu, Shicheng Zheng, Jiaya Jia
We show in this paper that the success of previous maximum a posterior (MAP) based blur removal methods partly stems from their respective intermediate steps, which implicitly or explicitly create an unnatural representation containing salient image structures.
Ranked #13 on Deblurring on RealBlur-R (trained on GoPro) (SSIM (sRGB) metric)