1 code implementation • 28 May 2024 • Yunsong Wang, Tianxin Huang, Hanlin Chen, Gim Hee Lee
However, existing generalizable 3D Gaussian Splatting methods are largely confined to narrow-range interpolation between stereo images due to their heavy backbones, thus lacking the ability to accurately localize 3D Gaussian and support free-view synthesis across wide view range.
no code implementations • 10 Apr 2024 • Tianxin Huang, Zhiwen Yan, Yuyang Zhao, Gim Hee Lee
3D point cloud completion is designed to recover complete shapes from partially observed point clouds.
1 code implementation • 4 Mar 2024 • Chao Xu, Yang Liu, Jiazheng Xing, Weida Wang, Mingze Sun, Jun Dan, Tianxin Huang, Siyuan Li, Zhi-Qi Cheng, Ying Tai, Baigui Sun
In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating various dynamically audio-consistent talking faces, termed Listening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio.
1 code implementation • 27 Dec 2023 • Tianxin Huang, Qingyao Liu, Xiangrui Zhao, Jun Chen, Yong liu
As point clouds are 3D signals with permutation invariance, most existing works train their reconstruction networks by measuring shape differences with the average point-to-point distance between point clouds matched with predefined rules.
1 code implementation • 12 Dec 2023 • Jingyang Xiang, Siqi Li, JunHao Chen, Zhuangzhi Chen, Tianxin Huang, Linpeng Peng, Yong liu
Meanwhile, a sparsity strategy that gradually increases the percentage of N:M weight blocks is applied, which allows the network to heal from the pruning-induced damage progressively.
no code implementations • 21 Aug 2023 • Jun Chen, Haishan Ye, Mengmeng Wang, Tianxin Huang, Guang Dai, Ivor W. Tsang, Yong liu
This paper proposes a decentralized Riemannian conjugate gradient descent (DRCGD) method that aims at minimizing a global function over the Stiefel manifold.
no code implementations • 2 Jul 2023 • Jun Chen, Shipeng Bai, Tianxin Huang, Mengmeng Wang, Guanzhong Tian, Yong liu
In this paper, we propose a data-free mixed-precision compensation (DF-MPC) method to recover the performance of an ultra-low precision quantized model without any data and fine-tuning process.
1 code implementation • 27 Jun 2023 • Jianbiao Mei, Yu Yang, Mengmeng Wang, Tianxin Huang, Xuemeng Yang, Yong liu
However, how to effectively exploit the relationships between the semantic context in semantic segmentation and geometric structure in scene completion remains under exploration.
no code implementations • 4 May 2023 • Chao Xu, Shaoting Zhu, Junwei Zhu, Tianxin Huang, Jiangning Zhang, Ying Tai, Yong liu
More specifically, given a textured face as the source and the rendered face projected from the desired 3DMM coefficients as the target, our proposed Texture-Geometry-aware Diffusion Model decomposes the complex transfer problem into multi-conditional denoising process, where a Texture Attention-based module accurately models the correspondences between appearance and geometry cues contained in source and target conditions, and incorporate extra implicit information for high-fidelity talking face generation.
1 code implementation • ICCV 2023 • Jiangning Zhang, Xiangtai Li, Jian Li, Liang Liu, Zhucun Xue, Boshen Zhang, Zhengkai Jiang, Tianxin Huang, Yabiao Wang, Chengjie Wang
This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance.
no code implementations • CVPR 2023 • Tianxin Huang, Zhonggan Ding, Jiangning Zhang, Ying Tai, Zhenyu Zhang, Mingang Chen, Chengjie Wang, Yong liu
Specifically, we use the contrastive constraint to help CALoss learn a representation space with shape similarity, while we introduce the adversarial strategy to help CALoss mine differences between reconstructed results and ground truths.
1 code implementation • 3 Aug 2022 • Xiangrui Zhao, Sheng Yang, Tianxin Huang, Jun Chen, Teng Ma, Mingyang Li, Yong liu
To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segmentation and description model for 3D lines in LiDAR point cloud.
no code implementations • 16 Nov 2021 • Jun Chen, Tianxin Huang, Wenzhou Chen, Yong liu
During the training process of the neural network, we observe that its metric will also regularly converge to the linearly nearly Euclidean metric, which is consistent with the convergent behavior of linearly nearly Euclidean metrics under the Ricci-DeTurck flow.
no code implementations • 29 Sep 2021 • Jun Chen, Hanwen Chen, Jiangning Zhang, Yuang Liu, Tianxin Huang, Yong liu
Quantized Neural Networks (QNNs) aim at replacing full-precision weights $\boldsymbol{W}$ with quantized weights $\boldsymbol{\hat{W}}$, which make it possible to deploy large models to mobile and miniaturized devices easily.
no code implementations • 29 Sep 2021 • Jun Chen, Tianxin Huang, Wenzhou Chen, Yong liu
The Ricci flow is a method of manifold surgery, which can trim manifolds to more regular.
no code implementations • IEEE International Workshop on Intelligent Robots and Systems (IROS) 2021 • Hao Zou, Xuemeng Yang, Tianxin Huang, Chujuan Zhang, Yong liu, Wanlong Li, Feng Wen, Hongbo Zhang
An efficient 3D scene perception algorithm is a vital component for autonomous driving and robotics systems.
Ranked #6 on 3D Semantic Scene Completion on SemanticKITTI
1 code implementation • 23 Sep 2021 • Xuemeng Yang, Hao Zou, Xin Kong, Tianxin Huang, Yong liu, Wanlong Li, Feng Wen, Hongbo Zhang
Specifically, the network takes a raw point cloud as input, and merges the features from the segmentation branch into the completion branch hierarchically to provide semantic information.
Ranked #4 on 3D Semantic Scene Completion on SemanticKITTI
1 code implementation • 1 Jul 2021 • Lin Li, Xin Kong, Xiangrui Zhao, Tianxin Huang, Yong liu
We also present a two-step global semantic ICP to obtain the 3D pose (x, y, yaw) used to align the point cloud to improve matching performance.
Ranked #1 on Visual Place Recognition on KITTI
no code implementations • ICCV 2021 • Tianxin Huang, Hao Zou, Jinhao Cui, Xuemeng Yang, Mengmeng Wang, Xiangrui Zhao, Jiangning Zhang, Yi Yuan, Yifan Xu, Yong liu
The RFE extracts multiple global features from the incomplete point clouds for different recurrent levels, and the FDC generates point clouds in a coarse-to-fine pipeline.