Inter-Region Affinity Distillation for Road Marking Segmentation

Apr 11, 2020
Yuenan Hou, Zheng Ma, Chunxiao Liu, Tak-Wai Hui, Chen Change Loy

* 10 pages, 10 figures; This paper is accepted by CVPR 2020; Our code is available at https://github.com/cardwing/Codes-for-IntRA-KD 

  Access Model/Code and Paper
Feature Pyramid Grids

Apr 07, 2020
Kai Chen, Yuhang Cao, Chen Change Loy, Dahua Lin, Christoph Feichtenhofer

* Technical report 

  Access Model/Code and Paper
Self-Supervised Scene De-occlusion

Apr 06, 2020
Xiaohang Zhan, Xingang Pan, Bo Dai, Ziwei Liu, Dahua Lin, Chen Change Loy

* Accepted to CVPR 2020 as oral. Project page: https://xiaohangzhan.github.io/projects/deocclusion/ 

  Access Model/Code and Paper
Learning to Cluster Faces via Confidence and Connectivity Estimation

Apr 03, 2020
Lei Yang, Dapeng Chen, Xiaohang Zhan, Rui Zhao, Chen Change Loy, Dahua Lin

* 8 pages, 6 figures, CVPR 2020 

  Access Model/Code and Paper
TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting

Apr 01, 2020
Zhuoqian Yang, Wentao Zhu, Wayne Wu, Chen Qian, Qiang Zhou, Bolei Zhou, Chen Change Loy

* Accepted by CVPR 2020. The first three authors contributed equally. Project page: https://yzhq97.github.io/transmomo/ 

  Access Model/Code and Paper
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation

Mar 31, 2020
Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin, Chen Change Loy, Ping Luo

* 1) Precise GAN-inversion by discriminator-guided generator finetuning. 2) A versatile way for high-quality image restoration and manipulation. Code: https://github.com/XingangPan/deep-generative-prior 

  Access Model/Code and Paper
1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation

Mar 17, 2020
Yu Liu, Guanglu Song, Yuhang Zang, Yan Gao, Enze Xie, Junjie Yan, Chen Change Loy, Xiaogang Wang


  Access Model/Code and Paper
Residual Knowledge Distillation

Feb 21, 2020
Mengya Gao, Yujun Shen, Quanquan Li, Chen Change Loy

* 9 pages, 3 figures, 3 tables 

  Access Model/Code and Paper
Real or Not Real, that is the Question

Feb 12, 2020
Yuanbo Xiangli, Yubin Deng, Bo Dai, Chen Change Loy, Dahua Lin

* ICLR2020 spotlight. 1) train GAN by maximizing kl-divergence. 2) train non-progressive GAN (DCGAN) architecture at 1024*1024 resolution 

  Access Model/Code and Paper
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

Jan 19, 2020
Chunle Guo, Chongyi Li, Jichang Guo, Chen Change Loy, Junhui Hou, Sam Kwong, Runmin Cong


  Access Model/Code and Paper
Everybody's Talkin': Let Me Talk as You Want

Jan 15, 2020
Linsen Song, Wayne Wu, Chen Qian, Ran He, Chen Change Loy

* Technical report. Project page: https://wywu.github.io/projects/EBT/EBT.html 

  Access Model/Code and Paper
DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection

Jan 09, 2020
Liming Jiang, Wayne Wu, Ren Li, Chen Qian, Chen Change Loy

* Project page: https://liming-jiang.com/projects/DrF1/DrF1.html 

  Access Model/Code and Paper
EcoNAS: Finding Proxies for Economical Neural Architecture Search

Jan 05, 2020
Dongzhan Zhou, Xinchi Zhou, Wenwei Zhang, Chen Change Loy, Shuai Yi, Xuesen Zhang, Wanli Ouyang

* Technical Report 

  Access Model/Code and Paper
Side-Aware Boundary Localization for More Precise Object Detection

Dec 09, 2019
Jiaqi Wang, Wenwei Zhang, Yuhang Cao, Kai Chen, Jiangmiao Pang, Tao Gong, Jianping Shi, Chen Change Loy, Dahua Lin

* Technical Report 

  Access Model/Code and Paper
Learning to Synthesize Fashion Textures

Nov 18, 2019
Wu Shi, Tak-Wai Hui, Ziwei Liu, Dahua Lin, Chen Change Loy


  Access Model/Code and Paper
Robust Multi-Modality Multi-Object Tracking

Sep 09, 2019
Wenwei Zhang, Hui Zhou, Shuyang Sun, Zhe Wang, Jianping Shi, Chen Change Loy

* To appear in ICCV 2019. Code and models are available at https://github.com/ZwwWayne/mmMOT 

  Access Model/Code and Paper
Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild

Aug 20, 2019
Yu Rong, Ziwei Liu, Cheng Li, Kaidi Cao, Chen Change Loy

* To appear in ICCV 2019. Code and models are available at https://penincillin.github.io/dct_iccv2019 

  Access Model/Code and Paper
One-shot Face Reenactment

Aug 05, 2019
Yunxuan Zhang, Siwei Zhang, Yue He, Cheng Li, Chen Change Loy, Ziwei Liu

* To appear in BMVC 2019 as a spotlight presentation. Code and models are available at: https://github.com/bj80heyue/One_Shot_Face_Reenactment 

  Access Model/Code and Paper
Learning Lightweight Lane Detection CNNs by Self Attention Distillation

Aug 02, 2019
Yuenan Hou, Zheng Ma, Chunxiao Liu, Chen Change Loy

* 9 pages, 8 figures; This paper is accepted by ICCV 2019; Our code is available at https://github.com/cardwing/Codes-for-Lane-Detection 

  Access Model/Code and Paper
MMDetection: Open MMLab Detection Toolbox and Benchmark

Jun 17, 2019
Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin

* Technical report of MMDetection. 11 pages 

  Access Model/Code and Paper
Disentangling Content and Style via Unsupervised Geometry Distillation

May 11, 2019
Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy

* Accepted to ICLR 2019 Workshop 

  Access Model/Code and Paper
Deep Flow-Guided Video Inpainting

May 08, 2019
Rui Xu, Xiaoxiao Li, Bolei Zhou, Chen Change Loy

* cvpr'19 

  Access Model/Code and Paper
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks

May 07, 2019
Xintao Wang, Kelvin C. K. Chan, Ke Yu, Chao Dong, Chen Change Loy

* To appear in CVPR 2019 Workshop. The winners in all four tracks in the NTIRE 2019 video restoration and enhancement challenges. Project page: https://xinntao.github.io/projects/EDVR , Code: https://github.com/xinntao/EDVR 

  Access Model/Code and Paper
CARAFE: Content-Aware ReAssembly of FEatures

May 07, 2019
Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin

* Technical Report 

  Access Model/Code and Paper
Learning to Cluster Faces on an Affinity Graph

May 05, 2019
Lei Yang, Xiaohang Zhan, Dapeng Chen, Junjie Yan, Chen Change Loy, Dahua Lin

* 8 pages, 8 figures, CVPR 2019 

  Access Model/Code and Paper
Self-Supervised Learning via Conditional Motion Propagation

Apr 25, 2019
Xiaohang Zhan, Xingang Pan, Ziwei Liu, Dahua Lin, Chen Change Loy

* In CVPR 2019. More details at the project page: http://mmlab.ie.cuhk.edu.hk/projects/CMP/ 

  Access Model/Code and Paper
Path-Restore: Learning Network Path Selection for Image Restoration

Apr 23, 2019
Ke Yu, Xintao Wang, Chao Dong, Xiaoou Tang, Chen Change Loy

* Project page: https://yuke93.github.io/Path-Restore/ 

  Access Model/Code and Paper
TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation

Apr 21, 2019
Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy

* Accepted to CVPR 2019. Project page: https://wywu.github.io/projects/TGaGa/TGaGa.html 

  Access Model/Code and Paper