Picture for Wenxiong Kang

Wenxiong Kang

CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo

May 17, 2023
Weitao Chen, Hongbin Xu, Zhipeng Zhou, Yang Liu, Baigui Sun, Wenxiong Kang, Xuansong Xie

Figure 1 for CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo

Figure 2 for CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo

Figure 3 for CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo

Figure 4 for CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo

* Accepted by IJCAI-23

Access Paper or Ask Questions

Semi-supervised Deep Multi-view Stereo

Jul 24, 2022
Hongbin Xu, Zhipeng Zhou, Weitao Cheng, Baigui Sun, Hao Li, Wenxiong Kang

Figure 1 for Semi-supervised Deep Multi-view Stereo

Figure 2 for Semi-supervised Deep Multi-view Stereo

Figure 3 for Semi-supervised Deep Multi-view Stereo

Figure 4 for Semi-supervised Deep Multi-view Stereo

* Draft version. Still in submission

Access Paper or Ask Questions

From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition

Dec 15, 2021
Wenxiong Kang, Yuting Lu, Dejian Li, Wei Jia

Figure 1 for From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition

Figure 2 for From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition

Figure 3 for From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition

Figure 4 for From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition

* IEEE transactions on information forensics and security 14.4 (2018): 858-869
* 11 pages

Access Paper or Ask Questions

Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark

Dec 02, 2021
Lin Nie, Lingbo Liu, Zhengtao Wu, Wenxiong Kang

Figure 1 for Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark

Figure 2 for Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark

Figure 3 for Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark

Figure 4 for Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark

* We proposed the first medium-scale benchmark for unconstrained face sketch synthesis

Access Paper or Ask Questions

Digging into Uncertainty in Self-supervised Multi-view Stereo

Sep 08, 2021
Hongbin Xu, Zhipeng Zhou, Yali Wang, Wenxiong Kang, Baigui Sun, Hao Li, Yu Qiao

Figure 1 for Digging into Uncertainty in Self-supervised Multi-view Stereo

Figure 2 for Digging into Uncertainty in Self-supervised Multi-view Stereo

Figure 3 for Digging into Uncertainty in Self-supervised Multi-view Stereo

Figure 4 for Digging into Uncertainty in Self-supervised Multi-view Stereo

* This paper is accepted by ICCV-21 as a poster presentation

Access Paper or Ask Questions

Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation

Apr 12, 2021
Hongbin Xu, Zhipeng Zhou, Yu Qiao, Wenxiong Kang, Qiuxia Wu

* This paper is accepted by AAAI-21 with a Distinguished Paper Award

Access Paper or Ask Questions

Dynamic Group Convolution for Accelerating Convolutional Neural Networks

Jul 10, 2020
Zhuo Su, Linpu Fang, Wenxiong Kang, Dewen Hu, Matti Pietikäinen, Li Liu

Figure 1 for Dynamic Group Convolution for Accelerating Convolutional Neural Networks

Figure 2 for Dynamic Group Convolution for Accelerating Convolutional Neural Networks

Figure 3 for Dynamic Group Convolution for Accelerating Convolutional Neural Networks

Figure 4 for Dynamic Group Convolution for Accelerating Convolutional Neural Networks

* 21 pages, 10 figures

Access Paper or Ask Questions

JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image

Jul 10, 2020
Linpu Fang, Xingyan Liu, Li Liu, Hang Xu, Wenxiong Kang

Figure 1 for JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image

Figure 2 for JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image

Figure 3 for JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image

Figure 4 for JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image

* Accepted by ECCV2020 as a Spotlight paper

Access Paper or Ask Questions