no code implementations • ECCV 2020 • Fang Liu, Changqing Zou, Xiaoming Deng, Ran Zuo, Yu-Kun Lai, Cuixia Ma, Yong-Jin Liu, Hongan Wang
Sketch-based image retrieval (SBIR) has been a popular research topic in recent years.
no code implementations • 15 Apr 2024 • Tong Wu, Jia-Mu Sun, Yu-Kun Lai, Yuewen Ma, Leif Kobbelt, Lin Gao
To address these issues, we introduce DeferredGS, a method for decoupling and editing the Gaussian splatting representation using deferred shading.
no code implementations • 15 Mar 2024 • Tian-Xing Xu, WenBo Hu, Yu-Kun Lai, Ying Shan, Song-Hai Zhang
3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering.
no code implementations • 7 Feb 2024 • Lin Gao, Jie Yang, Bo-Tao Zhang, Jia-Mu Sun, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai
Based on this representation, we further introduce a large-scale Gaussian deformation technique to enable deformable GS, which alters the parameters of 3D Gaussians according to the manipulation of the associated mesh.
no code implementations • 6 Feb 2024 • Haotian Yang, Mingwu Zheng, Chongyang Ma, Yu-Kun Lai, Pengfei Wan, Haibin Huang
In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling.
no code implementations • 10 Dec 2023 • Yi Wang, Jian Ma, Ruizhi Shao, Qiao Feng, Yu-Kun Lai, Yebin Liu, Kun Li
To keep the generated clothing consistent with the target text, we propose a semantic-confidence strategy for clothing that can eliminate the non-clothing content generated by the model.
no code implementations • 10 Dec 2023 • Yuanwang Yang, Qiao Feng, Yu-Kun Lai, Kun Li
In this paper, we propose R2Human, the first approach for real-time inference and rendering of photorealistic 3D human appearance from a single image.
no code implementations • 9 Nov 2023 • Haokun Zhu, Juang Ian Chong, Teng Hu, Ran Yi, Yu-Kun Lai, Paul L. Rosin
Vector graphics are widely used in graphical designs and have received more and more attention.
no code implementations • 2 Nov 2023 • Xiongzheng Li, Jinsong Zhang, Yu-Kun Lai, Jingyu Yang, Kun Li
To alleviate the ambiguity estimating 3D garments from monocular videos, we design a multi-hypothesis deformation module that learns spatial representations of multiple plausible deformations.
no code implementations • 30 Oct 2023 • Jinsong Zhang, Lingfeng Gu, Yu-Kun Lai, Xueyang Wang, Kun Li
To explore the potential spatio-temporal relationship, we propose spatio-temporal transformers to simultaneously extract trajectory information and fuse inter-person features in a hierarchical manner.
1 code implementation • ICCV 2023 • Shuang Song, Yuanbang Liang, Jing Wu, Yu-Kun Lai, Yipeng Qin
Thanks to our discovery of Feature Proliferation, the proposed feature rescaling method is less destructive and retains more useful image features than the truncation trick, as it is more fine-grained and works in a lower-level feature space rather than a high-level latent space.
no code implementations • 8 Sep 2023 • Haotian Yang, Mingwu Zheng, Wanquan Feng, Haibin Huang, Yu-Kun Lai, Pengfei Wan, Zhongyuan Wang, Chongyang Ma
Specifically, TRAvatar is trained with dynamic image sequences captured in a Light Stage under varying lighting conditions, enabling realistic relighting and real-time animation for avatars in diverse scenes.
no code implementations • 4 Jul 2023 • Chuanyu Pan, Guowei Yang, TaiJiang Mu, Yu-Kun Lai
With the booming of virtual reality (VR) technology, there is a growing need for customized 3D avatars.
1 code implementation • CVPR 2023 • Ran Yi, Haoyuan Tian, Zhihao Gu, Yu-Kun Lai, Paul L. Rosin
To fill the gap in the field of artistic image aesthetics assessment (AIAA), we first introduce a large-scale AIAA dataset: Boldbrush Artistic Image Dataset (BAID), which consists of 60, 337 artistic images covering various art forms, with more than 360, 000 votes from online users.
no code implementations • ICCV 2023 • Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai, Song-Hai Zhang
To address these issues, we present MBPTrack, which adopts a Memory mechanism to utilize past information and formulates localization in a coarse-to-fine scheme using Box Priors given in the first frame.
no code implementations • 9 Mar 2023 • Xintong Yang, Ze Ji, Jing Wu, Yu-Kun Lai
As a popular concept proposed in the field of psychology, affordance has been regarded as one of the important abilities that enable humans to understand and interact with the environment.
no code implementations • 24 Feb 2023 • Bin Liu, Xiaolin Wei, Bo Li, Junjie Cao, Yu-Kun Lai
In this paper, a novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention.
no code implementations • 16 Feb 2023 • Lin Gao, Jia-Mu Sun, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Jie Yang
We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level.
no code implementations • CVPR 2023 • Xiaokun Sun, Qiao Feng, Xiongzheng Li, Jinsong Zhang, Yu-Kun Lai, Jingyu Yang, Kun Li
3D human body representation learning has received increasing attention in recent years.
2 code implementations • ICCV 2023 • Ren-Wu Li, Ling-Xiao Zhang, Chunpeng Li, Yu-Kun Lai, Lin Gao
E3Sym establishes robust point correspondences through the use of E(3) invariant features extracted from a lightweight neural network, from which the dense symmetry prediction is produced.
no code implementations • CVPR 2023 • Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai, Song-Hai Zhang
Therefore, contextual information across two consecutive frames is crucial for effective object tracking.
1 code implementation • 19 Jul 2022 • Xintong Yang, Ze Ji, Jing Wu, Yu-Kun Lai
Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks given only a task-completion reward signal.
1 code implementation • 13 Jun 2022 • Yuanbang Liang, Jing Wu, Yu-Kun Lai, Yipeng Qin
Despite the extensive studies on Generative Adversarial Networks (GANs), how to reliably sample high-quality images from their latent spaces remains an under-explored topic.
no code implementations • 5 Jun 2022 • Qiao Feng, Yebin Liu, Yu-Kun Lai, Jingyu Yang, Kun Li
Based on FOF, we design the first 30+FPS high-fidelity real-time monocular human reconstruction framework.
Ranked #2 on 3D Human Reconstruction on CustomHumans (using extra training data)
no code implementations • CVPR 2022 • Yi-Hua Huang, Yue He, Yu-Jie Yuan, Yu-Kun Lai, Lin Gao
We first pre-train a standard NeRF of the 3D scene to be stylized and replace its color prediction module with a style network to obtain a stylized NeRF.
1 code implementation • CVPR 2023 • Bo Li, Kaitao Xue, Bin Liu, Yu-Kun Lai
In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process.
no code implementations • CVPR 2022 • Yu-Jie Yuan, Yang-tian Sun, Yu-Kun Lai, Yuewen Ma, Rongfei Jia, Lin Gao
In this paper, we propose a method that allows users to perform controllable shape deformation on the implicit representation of the scene, and synthesizes the novel view images of the edited scene without re-training the network.
no code implementations • 25 Mar 2022 • Meihao Kong, Jing Huo, Wenbin Li, Jing Wu, Yu-Kun Lai, Yang Gao
(2) Using iterative magnitude pruning, we find the matching subnetworks at 89. 2% sparsity in AdaIN and 73. 7% sparsity in SANet, which demonstrates that style transfer models can play lottery tickets too.
1 code implementation • 8 Feb 2022 • Ran Yi, Yong-Jin Liu, Yu-Kun Lai, Paul L. Rosin
In this paper, we propose a novel method to automatically transform face photos to portrait drawings using unpaired training data with two new features; i. e., our method can (1) learn to generate high quality portrait drawings in multiple styles using a single network and (2) generate portrait drawings in a "new style" unseen in the training data.
no code implementations • 18 Jan 2022 • Kunhao Yuan, Gerald Schaefer, Yu-Kun Lai, Yifan Wang, Xiyao Liu, Lin Guan, Hui Fang
Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS) methods.
no code implementations • 16 Jan 2022 • Zipeng Ye, Mengfei Xia, Ran Yi, Juyong Zhang, Yu-Kun Lai, Xuwei Huang, Guoxin Zhang, Yong-Jin Liu
In this paper, we present a dynamic convolution kernel (DCK) strategy for convolutional neural networks.
no code implementations • CVPR 2022 • Hao Zhao, Jinsong Zhang, Yu-Kun Lai, Zerong Zheng, Yingdi Xie, Yebin Liu, Kun Li
To cope with the complexity of textures and generate photo-realistic results, we propose a reference-based neural rendering network and exploit a bottom-up sharpening-guided fine-tuning strategy to obtain detailed textures.
no code implementations • 28 Oct 2021 • Kevin Maher, Zeyuan Huang, Jiancheng Song, Xiaoming Deng, Yu-Kun Lai, Cuixia Ma, Hao Wang, Yong-Jin Liu, Hongan Wang
We further studied the usability of the system by speaking novices and experts on assisting analysis of inspirational speech effectiveness.
no code implementations • IEEE Transactions on Visualization and Computer Graphics 2021 • Yun Zhang, Yu-Kun Lai, and Fang-Lue Zhang, Member, IEEE
By analyzing the irregular boundary, we construct a piecewise rectangular boundary.
no code implementations • 27 Jun 2021 • Yang-tian Sun, Hao-Zhi Huang, Xuan Wang, Yu-Kun Lai, Wei Liu, Lin Gao
Moreover, we introduce a concise temporal loss in the training stage to suppress the detail flickering that is made more visible due to high-quality dynamic details generated by our method.
1 code implementation • CVPR 2021 • Dongyu She, Yu-Kun Lai, Gaoxiong Yi, Kun Xu
The first LA-GCN module constructs an aesthetics-related graph in the coordinate space and performs reasoning over spatial nodes.
1 code implementation • 25 May 2021 • Tian-Xing Xu, Yuan-Chen Guo, Zhiqiang Li, Ge Yu, Yu-Kun Lai, Song-Hai Zhang
Place recognition plays an essential role in the field of autonomous driving and robot navigation.
Ranked #4 on 3D Place Recognition on CS-Campus3D
2 code implementations • 12 May 2021 • Xintong Yang, Ze Ji, Jing Wu, Yu-Kun Lai
This work re-implements the OpenAI Gym multi-goal robotic manipulation environment, originally based on the commercial Mujoco engine, onto the open-source Pybullet engine.
1 code implementation • CVPR 2021 • Jinsong Zhang, Kun Li, Yu-Kun Lai, Jingyu Yang
The results of qualitative and quantitative experiments demonstrate the superiority of our model on human pose transfer.
no code implementations • 23 Feb 2021 • Lan Chen, Lin Gao, Jie Yang, Shibiao Xu, Juntao Ye, Xiaopeng Zhang, Yu-Kun Lai
Moreover, as such methods only add details, they require coarse meshes to be close to fine meshes, which can be either impossible, or require unrealistic constraints when generating fine meshes.
no code implementations • ICCV 2021 • Ming-Xian Lin, Jie Yang, He Wang, Yu-Kun Lai, Rongfei Jia, Binqiang Zhao, Lin Gao
Inspired by the great success in recent contrastive learning works on self-supervised representation learning, we propose a novel IBSR pipeline leveraging contrastive learning.
no code implementations • ICCV 2021 • Qian Xie, Yu-Kun Lai, Jing Wu, Zhoutao Wang, Dening Lu, Mingqiang Wei, Jun Wang
Hough voting, as has been demonstrated in VoteNet, is effective for 3D object detection, where voting is a key step.
1 code implementation • ICCV 2021 • Zhoutao Wang, Qian Xie, Yu-Kun Lai, Jing Wu, Kun Long, Jun Wang
To deal with sparsity in outdoor 3D point clouds, we propose to perform Hough voting on multi-level features to get more vote centers and retain more useful information, instead of voting only on the final level feature as in previous methods.
1 code implementation • 13 Dec 2020 • Kun Li, Jinsong Zhang, Yebin Liu, Yu-Kun Lai, Qionghai Dai
In each block, we propose a pose-guided non-local attention (PoNA) mechanism with a long-range dependency scheme to select more important regions of image features to transfer.
no code implementations • 4 Dec 2020 • Jie Yang, Lin Gao, Qingyang Tan, Yihua Huang, Shihong Xia, Yu-Kun Lai
The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales.
no code implementations • 13 Oct 2020 • Lin Gao, Tong Wu, Yu-Jie Yuan, Ming-Xian Lin, Yu-Kun Lai, Hao Zhang
We introduce a conditional autoregressive model for texture generation, which can be conditioned on both part geometry and textures already generated for other parts to achieve texture compatibility.
Graphics
1 code implementation • 2 Oct 2020 • Rao Fu, Jie Yang, Jiawei Sun, Fang-Lue Zhang, Yu-Kun Lai, Lin Gao
Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query shape in a repository with models belonging to the same class, which requires shape descriptors to be capable of representing detailed geometric information to discriminate shapes with globally similar structures.
no code implementations • 1 Sep 2020 • Paul L. Rosin, Yu-Kun Lai, David Mould, Ran Yi, Itamar Berger, Lars Doyle, Seungyong Lee, Chuan Li, Yong-Jin Liu, Amir Semmo, Ariel Shamir, Minjung Son, Holger Winnemoller
Despite the recent upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer, the state of performance evaluation in this field is limited, especially compared to the norms in the computer vision and machine learning communities.
1 code implementation • 12 Aug 2020 • Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao
While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structure, in a controllable manner.
1 code implementation • 12 Aug 2020 • Paul L. Rosin, Yu-Kun Lai
This paper describes a simple image-based method that applies engraving stylisation to portraits using ordered dithering.
no code implementations • 8 Jul 2020 • Kun Li, Jing Yang, Nianhong Jiao, Jinsong Zhang, Yu-Kun Lai
3D face reconstruction from a single image is a challenging problem, especially under partial occlusions and extreme poses.
2 code implementations • CVPRW 2020 • Matiur Rahman Minar, Thai Thanh Tuan, Heejune Ahn, Paul Rosin, Yu-Kun Lai
Recently proposed Image-based virtual try-on (VTON) approaches have several challenges regarding diverse human poses and cloth styles.
Ranked #1 on Virtual Try-on on VITON (IS metric)
no code implementations • CVPRW 2020 • Matiur Rahman Minar, Thai Thanh Tuan, Heejune Ahn, Paul Rosin, Yu-Kun Lai
Due to the correspondence, resulting 3D clothing models can be easily transferred to the target human models with different poses and shapes estimated from 2D images.
1 code implementation • ICCV 2021 • Jing Huo, Shiyin Jin, Wenbin Li, Jing Wu, Yu-Kun Lai, Yinghuan Shi, Yang Gao
In this paper, we make a new assumption that image features from the same semantic region form a manifold and an image with multiple semantic regions follows a multi-manifold distribution.
1 code implementation • CVPR 2020 • Qian Xie, Yu-Kun Lai, Jing Wu, Zhoutao Wang, Yiming Zhang, Kai Xu, Jun Wang
We demonstrate these by capturing contextual information at patch, object and scene levels.
no code implementations • 24 Mar 2020 • Min Shi, Jia-Qi Zhang, Shu-Yu Chen, Lin Gao, Yu-Kun Lai, Fang-Lue Zhang
The color transform network takes the target line art images as well as the line art and color images of one or more reference images as input, and generates corresponding target color images.
1 code implementation • 15 Mar 2020 • Zipeng Ye, Mengfei Xia, Yanan sun, Ran Yi, MinJing Yu, Juyong Zhang, Yu-Kun Lai, Yong-Jin Liu
The most challenging issue for our system is that the source domain of face photos (characterized by normal 2D faces) is significantly different from the target domain of 3D caricatures (characterized by 3D exaggerated face shapes and textures).
no code implementations • 19 Feb 2020 • Yun-Peng Xiao, Yu-Kun Lai, Fang-Lue Zhang, Chunpeng Li, Lin Gao
However, the performance for different applications largely depends on the representation used, and there is no unique representation that works well for all applications.
Graphics
no code implementations • 7 Jan 2020 • Haodi Hou, Jing Huo, Jing Wu, Yu-Kun Lai, Yang Gao
Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo.
no code implementations • 1 Nov 2019 • Yi-Ling Qiao, Lin Gao, Shu-Zhi Liu, Ligang Liu, Yu-Kun Lai, Xilin Chen
In this paper, we propose \YL{a} learning-based approach to intrinsic reflectional symmetry detection.
no code implementations • 30 Oct 2019 • Yi-Ling Qiao, Lin Gao, Jie Yang, Paul L. Rosin, Yu-Kun Lai, Xilin Chen
3D models are commonly used in computer vision and graphics.
1 code implementation • 15 Oct 2019 • Lin Gao, Ling-Xiao Zhang, Hsien-Yu Meng, Yi-Hui Ren, Yu-Kun Lai, Leif Kobbelt
In this paper, we present a novel learning framework to automatically discover global planar reflective symmetry of a 3D shape.
no code implementations • 13 Aug 2019 • Lin Gao, Jie Yang, Tong Wu, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai, Hao Zhang
At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details.
1 code implementation • 7 Aug 2019 • Yu-Jie Yuan, Yu-Kun Lai, Jie Yang, Hongbo Fu, Lin Gao
3D shape analysis is an important research topic in computer vision and graphics.
no code implementations • 19 Jun 2019 • Jingyu Yang, Ji Xu, Kun Li, Yu-Kun Lai, Huanjing Yue, Jianzhi Lu, Hao Wu, Yebin Liu
This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes.
no code implementations • 21 Dec 2018 • Xiaoxiao Sun, Liang Zheng, Yu-Kun Lai, Jufeng Yang
In this work, we first systematically study the built-in gap between the web and standard datasets, i. e. different data distributions between the two kinds of data.
1 code implementation • 2019 IEEE/CVF International Conference on Computer Vision (ICCV) 2020 • Hsien-Yu Meng, Lin Gao, Yu-Kun Lai, Dinesh Manocha
Our approach results in a good volumetric representation that effectively tackles noisy point cloud datasets and is more robust for learning.
Graphics
no code implementations • 4 Oct 2018 • Yi-Ling Qiao, Lin Gao, Yu-Kun Lai, Shihong Xia
In this paper, we present a novel method for learning to synthesize 3D mesh animation sequences with long short-term memory (LSTM) blocks and mesh-based convolutional neural networks (CNNs).
Graphics
no code implementations • 17 Jul 2018 • David George, Xianguha Xie, Yu-Kun Lai, Gary KL Tam
First, we a propose a fast and relatively accurate feature-based deep learning model to provide dataset-wide segmentation predictions.
no code implementations • 9 Jul 2018 • Gareth Andrews, Sam Endean, Roberto Dyke, Yu-Kun Lai, Gwenno Ffrancon, Gary KL Tam
In this paper, we present a novel facial dynamic dataset HDFD which addresses the gap of existing datasets, including 4D funny faces with substantial non-isometric deformation, and 4D visual-audio faces of spoken phrases in a minority language (Welsh).
no code implementations • CVPR 2018 • Ran Yi, Yong-Jin Liu, Yu-Kun Lai
We propose an efficient Lloyd-like method with a splitting-merging scheme to compute a uniform tessellation on M, which induces the CSS in X. Theoretically our method has a good competitive ratio O(1).
6 code implementations • CVPR 2018 • Yang Chen, Yu-Kun Lai, Yong-Jin Liu
Two novel losses suitable for cartoonization are proposed: (1) a semantic content loss, which is formulated as a sparse regularization in the high-level feature maps of the VGG network to cope with substantial style variation between photos and cartoons, and (2) an edge-promoting adversarial loss for preserving clear edges.
1 code implementation • CVPR 2018 • Jufeng Yang, Dongyu She, Yu-Kun Lai, Paul L. Rosin, Ming-Hsuan Yang
The second branch utilizes both the holistic and localized information by coupling the sentiment map with deep features for robust classification.
1 code implementation • CVPR 2018 • Qianyi Wu, Juyong Zhang, Yu-Kun Lai, Jianmin Zheng, Jianfei Cai
Caricature is an art form that expresses subjects in abstract, simple and exaggerated view.
no code implementations • CVPR 2018 • Qingyang Tan, Lin Gao, Yu-Kun Lai, Shihong Xia
3D geometric contents are becoming increasingly popular.
Graphics
no code implementations • 13 Sep 2017 • Qingyang Tan, Lin Gao, Yu-Kun Lai, Jie Yang, Shihong Xia
Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing.
Graphics
no code implementations • 5 Sep 2017 • Lin Gao, Yu-Kun Lai, Jie Yang, Ling-Xiao Zhang, Leif Kobbelt, Shihong Xia
This along with a suitably chosen deformation basis including spatially localized deformation modes leads to significant advantages, including more meaningful, reliable, and efficient deformations because fewer and localized deformation modes are applied.
Graphics
1 code implementation • 31 Aug 2017 • Huihuang Zhao, Paul L. Rosin, Yu-Kun Lai
This paper presents an automatic image synthesis method to transfer the style of an example image to a content image.
no code implementations • CVPR 2017 • Yang Chen, Yong-Jin Liu, Yu-Kun Lai
Observing that it is challenging even for human subjects to give consistent scores for retargeting results of different source images, in this paper we propose a learning-based OQA method that predicts the ranking of a set of retargeted images with the same source image.
no code implementations • 15 Mar 2017 • Kun Li, Jingyu Yang, Yu-Kun Lai, Daoliang Guo
Non-rigid registration is challenging because it is ill-posed with high degrees of freedom and is thus sensitive to noise and outliers.