b'Xiaogang Wang'

research

∙ 06/25/2022

BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling

The learning and aggregation of multi-scale features are essential in em...

Yechao Bai, et al. ∙

research

∙ 06/22/2022

No Attention is Needed: Grouped Spatial-temporal Shift for Simple and Efficient Video Restorers

Video restoration, aiming at restoring clear frames from degraded videos...

Dasong Li, et al. ∙

research

∙ 06/19/2022

3D Object Detection for Autonomous Driving: A Review and New Outlooks

Autonomous driving, in recent years, has been receiving increasing atten...

Jiageng Mao, et al. ∙

research

∙ 06/09/2022

Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs

To build an artificial neural network like the biological intelligence s...

Jinguo Zhu, et al. ∙

research

∙ 06/02/2022

Siamese Image Modeling for Self-Supervised Vision Representation Learning

Self-supervised learning (SSL) has delivered superior performance on a v...

Chenxin Tao, et al. ∙

research

∙ 05/10/2022

Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network

With the growing popularity of smartphones, capturing high-quality image...

Dasong Li, et al. ∙

research

∙ 04/19/2022

Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer

Vision transformers have achieved great successes in many computer visio...

Wang Zeng, et al. ∙

research

∙ 03/29/2022

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

Unsupervised point cloud completion aims at estimating the corresponding...

Yingjie Cai, et al. ∙

research

∙ 03/25/2022

Point2Seq: Detecting 3D Objects as Sequences

We present a simple and effective framework, named Point2Seq, for 3D obj...

Yujing Xue, et al. ∙

research

∙ 03/24/2022

RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization

6-DoF object pose estimation from a monocular image is challenging, and ...

Yan Xu, et al. ∙

research

∙ 03/16/2022

Relational Self-Supervised Learning

Self-supervised Learning (SSL) including the mainstream contrastive lear...

Mingkai Zheng, et al. ∙

research

∙ 02/27/2022

Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling

The correct ego-motion estimation basically relies on the understanding ...

Yan Xu, et al. ∙

research

∙ 01/13/2022

Learning Semantic Abstraction of Shape via 3D Region of Interest

In this paper, we focus on the two tasks of 3D shape abstraction and sem...

Haiyue Fang, et al. ∙

research

∙ 12/05/2021

Dynamic Token Normalization Improves Vision Transformer

Vision Transformer (ViT) and its variants (e.g., Swin, PVT) have achieve...

Wenqi Shao, et al. ∙

research

∙ 12/02/2021

Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks

Biological intelligence systems of animals perceive the world by integra...

Xizhou Zhu, et al. ∙

research

∙ 11/29/2021

IDR: Self-Supervised Image Denoising via Iterative Data Refinement

The lack of large-scale noisy-clean image pairs restricts supervised den...

Yi Zhang, et al. ∙

research

∙ 11/26/2021

VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

Deep learning-based models encounter challenges when processing long-tai...

Changyao Tian, et al. ∙

research

∙ 11/24/2021

GreedyNASv2: Greedier Search with a Greedy Path Filter

Training a good supernet in one-shot NAS methods is difficult since the ...

Tao Huang, et al. ∙

research

∙ 10/10/2021

Weakly Supervised Contrastive Learning

Unsupervised visual representation learning has gained much attention fr...

Mingkai Zheng, et al. ∙

research

∙ 10/10/2021

Rethinking Noise Synthesis and Modeling in Raw Denoising

The lack of large-scale real raw image denoising dataset gives rise to c...

Yi Zhang, et al. ∙

research

∙ 09/07/2021

FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting

Transformer, as a strong and flexible architecture for modelling long-ra...

Rui Liu, et al. ∙

research

∙ 08/23/2021

Voxel-based Network for Shape Completion by Leveraging Edge Generation

Deep learning technique has yielded significant improvements in point cl...

Xiaogang Wang, et al. ∙

research

∙ 08/18/2021

LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector

Stereo-based 3D detection aims at detecting 3D object bounding boxes fro...

Xiaoyang Guo, et al. ∙

research

∙ 07/20/2021

ReSSL: Relational Self-Supervised Learning with Weak Augmentation

Self-supervised Learning (SSL) including the mainstream contrastive lear...

Mingkai Zheng, et al. ∙

research

∙ 06/25/2021

Vision Transformer Architecture Search

Recently, transformers have shown great superiority in solving computer ...

Xiu Su, et al. ∙

research

∙ 06/04/2021

Scalable Transformers for Neural Machine Translation

Transformer has been widely adopted in Neural Machine Translation (NMT) ...

Peng Gao, et al. ∙

research

∙ 05/21/2021

ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search

Human pose estimation has achieved significant progress in recent years....

Lumin Xu, et al. ∙

research

∙ 04/22/2021

Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation

While accurate lip synchronization has been achieved for arbitrary-subje...

Hang Zhou, et al. ∙

research

∙ 04/14/2021

Decoupled Spatial-Temporal Transformer for Video Inpainting

Video inpainting aims to fill the given spatiotemporal holes with realis...

Rui Liu, et al. ∙

research

∙ 04/13/2021

Visually Informed Binaural Audio Generation without Binaural Audios

Stereophonic audio, especially binaural audio, plays an essential role i...

Xudong Xu, et al. ∙

research

∙ 04/08/2021

Semantic Scene Completion via Integrating Instances and Scene in-the-Loop

Semantic Scene Completion aims at reconstructing a complete 3D scene wit...

Yingjie Cai, et al. ∙

research

∙ 03/31/2021

Fixing the Teacher-Student Knowledge Discrepancy in Distillation

Training a small student network with the guidance of a larger teacher n...

Jiangfan Han, et al. ∙

research

∙ 03/24/2021

Learning Fine-Grained Segmentation of 3D Shapes without Part Labels

Learning-based 3D shape segmentation is usually formulated as a semantic...

Xiaogang Wang, et al. ∙

research

∙ 03/14/2021

DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network

Conditional generative adversarial networks (cGANs) target at synthesizi...

Rui Liu, et al. ∙

research

∙ 01/31/2021

PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection

3D object detection is receiving increasing attention from both industry...

Shaoshuai Shi, et al. ∙

research

∙ 01/19/2021

Fast Convergence of DETR with Spatially Modulated Co-Attention

The recently proposed Detection Transformer (DETR) model successfully ap...

Peng Gao, et al. ∙

research

∙ 01/08/2021

Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction

Multi-scale representations deeply learned via convolutional neural netw...

Dan Xu, et al. ∙

research

∙ 12/18/2020

A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection

Both high-level and high-resolution feature representations are of great...

Jianbo Liu, et al. ∙

research

∙ 11/18/2020

End-to-End Object Detection with Adaptive Clustering Transformer

End-to-end Object Detection with Transformer (DETR)proposes to perform o...

Minghang Zheng, et al. ∙

research

∙ 10/17/2020

A Self-supervised Cascaded Refinement Network for Point Cloud Completion

Point clouds are often sparse and incomplete, which imposes difficulties...

Xiaogang Wang, et al. ∙

research

∙ 10/15/2020

Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

We propose a general framework for searching surrogate losses for mainst...

Hao Li, et al. ∙

research

∙ 10/08/2020

Deformable DETR: Deformable Transformers for End-to-End Object Detection

DETR has been recently proposed to eliminate the need for many hand-desi...

Xizhou Zhu, et al. ∙

research

∙ 08/04/2020

Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions

We propose a novel algorithm, named Open-Edit, which is the first attemp...

Xihui Liu, et al. ∙

research

∙ 08/02/2020

Point Cloud Completion by Learning Shape Priors

In view of the difficulty in reconstructing object details in point clou...

Xiaogang Wang, et al. ∙

research

∙ 07/25/2020

Gradient Regularized Contrastive Learning for Continual Domain Adaptation

Human beings can quickly adapt to environmental changes by leveraging le...

Peng Su, et al. ∙

research

∙ 07/20/2020

Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation

Stereophonic audio is an indispensable ingredient to enhance human audit...

Hang Zhou, et al. ∙

research

∙ 06/10/2020

3D Human Mesh Regression with Dense Correspondence

Estimating 3D mesh of the human body from a single 2D image is an import...

Wang Zeng, et al. ∙

research

∙ 05/05/2020

StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching

Large-scale synthetic datasets are beneficial to stereo matching but usu...

Rui Liu, et al. ∙

research

∙ 04/07/2020

Cascaded Refinement Network for Point Cloud Completion

Point clouds are often sparse and incomplete. Existing shape completion ...

Xiaogang Wang, et al. ∙

research

∙ 03/17/2020

1st Place Solutions for OpenImage2019 – Object Detection and Instance Segmentation

This article introduces the solutions of the two champion teams, `MMfrui...

Yu Liu, et al. ∙

Xiaogang Wang

Featured Co-authors