Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Shijian Lu

Shijian Lu

WaveFill: A Wavelet-based Generation Network for Image Inpainting

Jul 23, 2021
Yingchen Yu, Fangneng Zhan, Shijian Lu, Jianxiong Pan, Feiying Ma, Xuansong Xie, Chunyan Miao

Figure 1 for WaveFill: A Wavelet-based Generation Network for Image Inpainting

Figure 2 for WaveFill: A Wavelet-based Generation Network for Image Inpainting

Figure 3 for WaveFill: A Wavelet-based Generation Network for Image Inpainting

Figure 4 for WaveFill: A Wavelet-based Generation Network for Image Inpainting

* 10 pages, 7 figures

Access Paper or Ask Questions

Domain Adaptive Video Segmentation via Temporal Consistency Regularization

Jul 23, 2021
Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu

Figure 1 for Domain Adaptive Video Segmentation via Temporal Consistency Regularization

Figure 2 for Domain Adaptive Video Segmentation via Temporal Consistency Regularization

Figure 3 for Domain Adaptive Video Segmentation via Temporal Consistency Regularization

Figure 4 for Domain Adaptive Video Segmentation via Temporal Consistency Regularization

* Accepted to ICCV 2021. Code is available at https://github.com/Dayan-Guan/DA-VSN

Access Paper or Ask Questions

SynLiDAR: Learning From Synthetic LiDAR Sequential Point Cloud for Semantic Segmentation

Jul 12, 2021
Aoran Xiao, Jiaxing Huang, Dayan Guan, Fangneng Zhan, Shijian Lu

Figure 1 for SynLiDAR: Learning From Synthetic LiDAR Sequential Point Cloud for Semantic Segmentation

Figure 2 for SynLiDAR: Learning From Synthetic LiDAR Sequential Point Cloud for Semantic Segmentation

Figure 3 for SynLiDAR: Learning From Synthetic LiDAR Sequential Point Cloud for Semantic Segmentation

Figure 4 for SynLiDAR: Learning From Synthetic LiDAR Sequential Point Cloud for Semantic Segmentation

Access Paper or Ask Questions

FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition

Jul 07, 2021
Kaiwen Cui, Gongjie Zhang, Fangneng Zhan, Jiaxing Huang, Shijian Lu

Figure 1 for FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition

Figure 2 for FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition

Figure 3 for FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition

Figure 4 for FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition

Access Paper or Ask Questions

Bi-level Feature Alignment for Versatile Image Translation and Manipulation

Jul 07, 2021
Fangneng Zhan, Yingchen Yu, Rongliang Wu, Kaiwen Cui, Aoran Xiao, Shijian Lu, Ling Shao

Figure 1 for Bi-level Feature Alignment for Versatile Image Translation and Manipulation

Figure 2 for Bi-level Feature Alignment for Versatile Image Translation and Manipulation

Figure 3 for Bi-level Feature Alignment for Versatile Image Translation and Manipulation

Figure 4 for Bi-level Feature Alignment for Versatile Image Translation and Manipulation

* Submitted to TPAMI

Access Paper or Ask Questions

Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification

Jul 06, 2021
Mengxi Jia, Xinhua Cheng, Shijian Lu, Jian Zhang

Figure 1 for Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification

Figure 2 for Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification

Figure 3 for Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification

Figure 4 for Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification

Access Paper or Ask Questions

Blind Image Super-Resolution via Contrastive Representation Learning

Jul 01, 2021
Jiahui Zhang, Shijian Lu, Fangneng Zhan, Yingchen Yu

Figure 1 for Blind Image Super-Resolution via Contrastive Representation Learning

Figure 2 for Blind Image Super-Resolution via Contrastive Representation Learning

Figure 3 for Blind Image Super-Resolution via Contrastive Representation Learning

Figure 4 for Blind Image Super-Resolution via Contrastive Representation Learning

Access Paper or Ask Questions

Sparse Needlets for Lighting Estimation with Spherical Transport Loss

Jun 24, 2021
Fangneng Zhan, Changgong Zhang, Wenbo Hu, Shijian Lu, Feiying Ma, Xuansong Xie, Ling Shao

Figure 1 for Sparse Needlets for Lighting Estimation with Spherical Transport Loss

Figure 2 for Sparse Needlets for Lighting Estimation with Spherical Transport Loss

Figure 3 for Sparse Needlets for Lighting Estimation with Spherical Transport Loss

Figure 4 for Sparse Needlets for Lighting Estimation with Spherical Transport Loss

* 11 pages, 7 figures

Access Paper or Ask Questions

Unbalanced Feature Transport for Exemplar-based Image Translation

Jun 19, 2021
Fangneng Zhan, Yingchen Yu, Kaiwen Cui, Gongjie Zhang, Shijian Lu, Jianxiong Pan, Changgong Zhang, Feiying Ma, Xuansong Xie, Chunyan Miao

Figure 1 for Unbalanced Feature Transport for Exemplar-based Image Translation

Figure 2 for Unbalanced Feature Transport for Exemplar-based Image Translation

Figure 3 for Unbalanced Feature Transport for Exemplar-based Image Translation

Figure 4 for Unbalanced Feature Transport for Exemplar-based Image Translation

* Accepted to CVPR 2021

Access Paper or Ask Questions

Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification

Jun 16, 2021
Zhipeng Luo, Xiaobing Zhang, Shijian Lu, Shuai Yi

Figure 1 for Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification

Figure 2 for Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification

Figure 3 for Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification

Figure 4 for Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification

Access Paper or Ask Questions

Spectral Unsupervised Domain Adaptation for Visual Recognition

Jun 11, 2021
Jingyi Zhang, Jiaxing Huang, Shijian Lu

Figure 1 for Spectral Unsupervised Domain Adaptation for Visual Recognition

Figure 2 for Spectral Unsupervised Domain Adaptation for Visual Recognition

Figure 3 for Spectral Unsupervised Domain Adaptation for Visual Recognition

Figure 4 for Spectral Unsupervised Domain Adaptation for Visual Recognition

Access Paper or Ask Questions

Category Contrast for Unsupervised Domain Adaptation in Visual Tasks

Jun 08, 2021
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu, Ling Shao

Figure 1 for Category Contrast for Unsupervised Domain Adaptation in Visual Tasks

Figure 2 for Category Contrast for Unsupervised Domain Adaptation in Visual Tasks

Figure 3 for Category Contrast for Unsupervised Domain Adaptation in Visual Tasks

Figure 4 for Category Contrast for Unsupervised Domain Adaptation in Visual Tasks

Access Paper or Ask Questions

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Jun 05, 2021
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

Figure 1 for RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Figure 2 for RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Figure 3 for RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Figure 4 for RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

Access Paper or Ask Questions

Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment

Jun 05, 2021
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

Figure 1 for Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment

Figure 2 for Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment

Figure 3 for Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment

Figure 4 for Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment

Access Paper or Ask Questions

I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

May 18, 2021
Chuhui Xue, Shijian Lu, Song Bai, Wenqing Zhang, Changhu Wang

Figure 1 for I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

Figure 2 for I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

Figure 3 for I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

Figure 4 for I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

Access Paper or Ask Questions

Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Apr 30, 2021
Yingchen Yu, Fangneng Zhan, Rongliang Wu, Jianxiong Pan, Kaiwen Cui, Shijian Lu, Feiying Ma, Xuansong Xie, Chunyan Miao

Figure 1 for Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Figure 2 for Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Figure 3 for Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Figure 4 for Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

* Major revison needed

Access Paper or Ask Questions

DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention

Mar 31, 2021
Jingyi Zhang, Jiaxing Huang, Zhipeng Luo, Gongjie Zhang, Shijian Lu

Figure 1 for DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention

Figure 2 for DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention

Figure 3 for DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention

Figure 4 for DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention

Access Paper or Ask Questions

Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection

Mar 28, 2021
Gongjie Zhang, Kaiwen Cui, Tzu-Yi Hung, Shijian Lu

Figure 1 for Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection

Figure 2 for Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection

Figure 3 for Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection

Figure 4 for Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection

* Codes will not be released due to confidentiality agreement. Published on WACV 2021. (https://openaccess.thecvf.com/content/WACV2021/papers/Zhang_Defect-GAN_High-Fidelity_Defect_Synthesis_for_Automated_Defect_Inspection_WACV_2021_paper.pdf)

Access Paper or Ask Questions

Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning

Mar 25, 2021
Gongjie Zhang, Zhipeng Luo, Kaiwen Cui, Shijian Lu

Figure 1 for Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning

Figure 2 for Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning

Figure 3 for Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning

Figure 4 for Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning

* Codes and data will be made publicly available in the future

Access Paper or Ask Questions

MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation

Mar 24, 2021
Jiaxing Huang, Dayan Guan, Shijian Lu, Aoran Xiao

Figure 1 for MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation

Figure 2 for MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation

Figure 3 for MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation

Figure 4 for MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation

* Submitted to PR

Access Paper or Ask Questions

Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Mar 03, 2021
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

Figure 1 for Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Figure 2 for Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Figure 3 for Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Figure 4 for Cross-View Regularization for Domain Adaptive Panoptic Segmentation

* Accepted to CVPR 2021 as an Oral Presentation

Access Paper or Ask Questions

FSDR: Frequency Space Domain Randomization for Domain Generalization

Mar 03, 2021
Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

Figure 1 for FSDR: Frequency Space Domain Randomization for Domain Generalization

Figure 2 for FSDR: Frequency Space Domain Randomization for Domain Generalization

Figure 3 for FSDR: Frequency Space Domain Randomization for Domain Generalization

Figure 4 for FSDR: Frequency Space Domain Randomization for Domain Generalization

* Accepted to CVPR2021

Access Paper or Ask Questions

Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links

Mar 01, 2021
Chuhui Xue, Shijian Lu, Steven Hoi

Figure 1 for Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links

Figure 2 for Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links

Figure 3 for Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links

Figure 4 for Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links

Access Paper or Ask Questions

FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation

Mar 01, 2021
Aoran Xiao, Xiaofei Yang, Shijian Lu, Dayan Guan, Jiaxing Huang

Figure 1 for FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation

Figure 2 for FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation

Figure 3 for FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation

Figure 4 for FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation

* 20 pages, 7 figures

Access Paper or Ask Questions

Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

Feb 27, 2021
Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu, Yanpeng Cao

Figure 1 for Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

Figure 2 for Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

Figure 3 for Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

Figure 4 for Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

Access Paper or Ask Questions

GMLight: Lighting Estimation via Geometric Distribution Approximation

Feb 20, 2021
Fangneng Zhan, Yingchen Yu, Rongliang Wu, Changgong Zhang, Shijian Lu, Ling Shao, Feiying Ma, Xuansong Xie

Figure 1 for GMLight: Lighting Estimation via Geometric Distribution Approximation

Figure 2 for GMLight: Lighting Estimation via Geometric Distribution Approximation

Figure 3 for GMLight: Lighting Estimation via Geometric Distribution Approximation

Figure 4 for GMLight: Lighting Estimation via Geometric Distribution Approximation

* 12 pages, 11 figures. arXiv admin note: text overlap with arXiv:2012.11116

Access Paper or Ask Questions

EMLight: Lighting Estimation via Spherical Distribution Approximation

Dec 21, 2020
Fangneng Zhan, Changgong Zhang, Yingchen Yu, Yuan Chang, Shijian Lu, Feiying Ma, Xuansong Xie

Figure 1 for EMLight: Lighting Estimation via Spherical Distribution Approximation

Figure 2 for EMLight: Lighting Estimation via Spherical Distribution Approximation

Figure 3 for EMLight: Lighting Estimation via Spherical Distribution Approximation

Figure 4 for EMLight: Lighting Estimation via Spherical Distribution Approximation

* Accepted to AAAI 2021

Access Paper or Ask Questions