1

Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation
Point cloud registration aims at estimating the geometric transformation between two point cloud scans, in which point-wise …
Ziming Wang, Xiaoliang Huo, Zhenghao Chen, Jing Zhang, Lu Sheng, Dong Xu
PDF Cite Code Project
Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation
SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling
Reconstructing a 3D shape based on a single sketch image is challenging due to the large domain gap between a sparse, irregular sketch …
Chenjian Gao, Qian Yu, Lu Sheng, Yi-Zhe Song, Dong Xu
PDF Cite Project
X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation
In computer vision, pre-training models based on largescale supervised learning have been proven effective over the past few years. …
Yinan He, Gengshi Huang, Siyu Chen, Jianing Teng, Wang Kun, Zhenfei Yin, Lu Sheng, Ziwei Liu, Yu Qiao, Jing Shao
PDF Cite
X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation
3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
Accepted by CVPR 2022, as Oral presentation.
Daigang Cai, Lichen Zhao, Jing Zhang, Lu Sheng, Dong Xu
PDF Cite Code Project Ranks in ScanRefer Benchmark
3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer
Accepted by AAAI 2022.
Buyu Li, Yongchi Zhao, Zhelun Shi, Lu Sheng
PDF Cite Dataset Project DOI
DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer
3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds
Accepted by ICCV 2021. 1st place (up to Oct. 10, 2021) in the ScanRefer Benchmark, winner for the 3D Object Localization Challenge at the CVPR 2021, 1st Workshop on Language for 3D Scenes.
Lichen Zhao, Daigang Cai, Lu Sheng, Dong Xu
PDF Cite Code Project DOI Ranks in ScanRefer Benchmark
3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds
StyleFormer: Real-time Arbitrary Style Transfer via Parametric Style Composition
In this work, we propose a new feed-forward arbitrary style transfer method, referred to as StyleFormer, which can simultaneously …
Xiaolei Wu, Zhihao Hu, Lu Sheng, Dong Xu
PDF Cite Code Project DOI
StyleFormer: Real-time Arbitrary Style Transfer via Parametric Style Composition
VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds
Accepted by ACM Multimedia 2021, as Oral presentation.
Guanze Liu, Yu Rong, Lu Sheng
PDF Cite Code Project DOI
VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds
Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
Accepted by CVPR 2021. A lightweight model with SOTA results on ScanNet V2 and SUN RGB-D datasets.
Bowen Cheng, Lu Sheng, Shaoshuai Shi, Ming Yang, Dong Xu
PDF Cite Code Project DOI Ranks in Papers with Code
Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
Accepted by CVPR 2021, as Oral Presentation. We host the ForgeryNet Challenge 2021 in ICCV 2021, The 3rd Workshop on Sensing, Understanding and Synthesizing Humans.
Yinan He, Bei Gan, Siyu Chen, Yichun Zhou, Guojun Yin, Luchuan Song, Lu Sheng, Jing Shao, Ziwei Liu
PDF Cite Dataset Project DOI ForgeryNet Challenge
ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis