PUBLICATIONS

Our lab does research in image processing and synthesis, low-level vision, 3D vision, and autonomous driving.
In particular, we are interested in cutting-edge AI based sensing technologies (Slides).
Some technical reports can be found here
* indicates joint first authors

Learning to Predict Vehicle Trajectories with Model-based Planning

Haoran Song, Di Luan, Wenchao Ding, Michael Yu Wang, and Qifeng Chen

Conference on Robot Learning (CoRL), 2021

Project Website

Dual-Camera Super-Resolution with Aligned Attention Modules

Tengfei Wang*, Jiaxin Xie*, Wenxiu Sun, Qiong Yan, and Qifeng Chen

International Conference on Computer Vision (ICCV), 2021

Full Oral Presentation (3.4% acceptance rate)

Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving

Xuanchi Ren*, Tao Yang*, Li Erran Li, Alexandre Alahi, and Qifeng Chen

International Conference on Computer Vision (ICCV), 2021

Xuanchi is an HKUST undergraduate.

Internal Video Inpainting by Implicit Long-range Propagation

Hao Ouyang*, Tengfei Wang*, and Qifeng Chen

International Conference on Computer Vision (ICCV), 2021

DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation

Maosheng Ye*, Shuangjie Xu*, Tongyi Cao, and Qifeng Chen

International Conference on Computer Vision (ICCV), 2021

Embedding Novel Views in a Single JPEG Image

Yue Wu*, Guotao Meng*, and Qifeng Chen

International Conference on Computer Vision (ICCV), 2021

IICNet: A Generic Framework for Reversible Image Conversion

Ka Leong Cheng*, Yueqi Xie*, and Qifeng Chen

International Conference on Computer Vision (ICCV), 2021

Normalized Human Pose Features for Human Action Video Alignment

Jingyuan Liu, Mingyi Shi, Qifeng Chen, Hongbo Fu, and Chiew-Lan Tai

International Conference on Computer Vision (ICCV), 2021

Full Oral Presentation (3.4% acceptance rate)

Enhanced Invertible Encoding for Learned Image Compression

Yueqi Xie*, Ka Leong Cheng*, and Qifeng Chen

ACM International Conference on Multimedia (ACM MM), 2021

Full Oral Presentation (9% acceptance rate)

Source Code

Deep Generative Priors with Non-deterministic Degradation

Unsupervised Portrait Shadow Removal via Generative Priors

Yingqing He*, Yazhou Xing*, Tianjia Zhang, and Qifeng Chen

ACM International Conference on Multimedia (ACM MM), 2021

Full Oral Presentation (9% acceptance rate)

Source Code

Stereo Waterdrop Removal with Row-wise Dilated Attention

Zifan Shi, Na Fan, Dit-Yan Yeung, and Qifeng Chen

International Conference on Intelligent Robots and Systems (IROS), 2021

Source Code

Joint Depth and Normal Estimation from Real-world Time-of-flight Raw Data

Rongrong Gao*, Na Fan*, Changlin Li, Wentao Liu, and Qifeng Chen

International Conference on Intelligent Robots and Systems (IROS), 2021

Please email Na Fan <nfanaa@connect.ust.hk> for the ToF-100 dataset (for academic purpose only).

Please email Rongrong Gao <rgaoaf@connect.ust.hk> for the source codes.

Stereo Matching by Self-supervision of Multiscopic Vision

Weihao Yuan, Yazhan Zhang, Bingkun Wu, Siyu Zhu, Ping Tan, Michael Yu Wang, and Qifeng Chen

International Conference on Intelligent Robots and Systems (IROS), 2021

Efficient internal learning for image manipulation (33x faster than SinGAN)

SinIR: Efficient General Image Manipulation with Single Image Reconstruction

Jihyeong Yoo and Qifeng Chen

International Conference on Machine Learning (ICML), 2021

Supplementary Material

Source Code

Invertible Image Signal Processing

Yazhou Xing*, Zian Qian*, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Project Website

Source Code

Robust Reflection Removal with Reflection-free Flash-only Cues

Chenyang Lei and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Source Code

Neural Camera Simulators

Hao Ouyang*, Zifan Shi*, Chenyang Lei, Ka Lung Law, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Source Code

TPCN: Temporal Point Cloud Networks for Motion Forecasting

Maosheng Ye, Tongyi Cao, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Image Inpainting with External-internal Learning and Monochromic Bottleneck

Tengfei Wang*, Hao Ouyang*, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Project Website

Source Code

Involution: Inverting the Inherence of Convolution for Visual Recognition

Duo Li, Jie Hu, Changhu Wang, Xiangtai Li, Qi She, Lei Zhu, Tong Zhang, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Source Code

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

Yisheng He, Haibin Huang, Haoqiang Fan, Qifeng Chen, and Jian Sun

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Full Oral Presentation (4% acceptance rate)

Source Code

Learning to Denoise Astronomical Images with U-nets

Antonia Vojtekova, Maggie Lieu, Ivan Valtchanov, Bruno Altieri, Lyndsay Old, Qifeng Chen, Filip Hroch

Monthly Notices of the Royal Astronomical Society (MNRAS), 2020

Source Code

Blind Video Temporal Consistency via Deep Video Prior

Chenyang Lei*, Yazhou Xing*, and Qifeng Chen

Conference on Neural Information Processing Systems (NeurIPS), 2020

Demo Video

Source Code

Project Website

Slides

Self-supervised Dance Video Synthesis Conditioned on Music

Xuanchi Ren, Haoran Li, Zijian Huang, and Qifeng Chen

ACM International Conference on Multimedia (ACM MM), 2020

Full Oral Presentation (9% acceptance rate)

Demo Video, Demo Video 2

Source Code

Xuanchi, Haoran, and Zijian are HKUST undergraduates.

Deep Reinforced Attention Learning for Quality-Aware Visual Recognition

Duo Li and Qifeng Chen

European Conference on Computer Vision (ECCV), 2020

PiP: Planning-informed Trajectory Prediction for Autonomous Driving

Haoran Song, Wenchao Ding, Yuxuan Chen, Shaojie Shen, Michael Yu Wang, and Qifeng Chen

European Conference on Computer Vision (ECCV), 2020

Project Website

Learning to Learn Parameterized Classification Networks for Scalable Input Images

Duo Li, Anbang Yao, and Qifeng Chen

European Conference on Computer Vision (ECCV), 2020

Source Code

PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer

Duo Li, Anbang Yao, and Qifeng Chen

European Conference on Computer Vision (ECCV), 2020

Source Code

Fully Convolutional Networks for Continuous Sign Language Recognition

Ka Leong CHENG, Zhaoyang Yang, Qifeng Chen, and Yu-Wing Tai

European Conference on Computer Vision (ECCV), 2020

Video Depth Estimation by Fusing Flow-to-Depth Proposals

Jiaxin Xie, Chenyang Lei, Zhuwen Li, Li Erran Li, and Qifeng Chen

International Conference on Intelligent Robots and Systems (IROS), 2020

Demo Video

Project Website

Source Code

Self-supervised Object Tracking with Cycle-consistent Siamese Networks

Weihao Yuan, Michael Yu Wang, and Qifeng Chen

International Conference on Intelligent Robots and Systems (IROS), 2020

Source Code

Depth Sensing Beyond LiDAR Range

Kai Zhang, Jiaxin Xie, Noah Snavely, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Project website

Source Code

Polarized Reflection Removal with Perfect Alignment in the Wild

Chenyang Lei, Xuhua Huang, Mengdi Zhang, Qiong Yan, Wenxiu Sun, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Project website

Source Code

Future Video Synthesis with Object Motion Prediction

Yue Wu, Rongrong Gao, Jaesik Park, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Demo Video

Supplementary Material

Source Code

MFuseNet: Robust Depth Estimation with Learned Multiscopic Fusion

Weihao Yuan, Rui Fan, Michael Yu Wang, and Qifeng Chen

International Conference on Robotics and Automation (ICRA), 2020

IEEE Robotics and Automation Letters, 2020

Project Website

Demo Video

Source Code

Hiding Video in Audio via Reversible Generative Models

Hyukyrul Yang*, Hao Ouyang*, Vladlen Koltun, and Qifeng Chen

International Conference on Computer Vision (ICCV), 2019

Slides

High-quality video reconstruction from raw sensor data.

Seeing Motion in the Dark

Chen Chen, Qifeng Chen, Minh Do, and Vladlen Koltun

International Conference on Computer Vision (ICCV), 2019

Full Oral Presentation (4.3% acceptance rate)

Demo Video

Source Code

The first dedicated video colorization method without any user input.

Fully Automatic Video Colorization with Self-Regularization and Diversity

Chenyang Lei and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Project Website

Demo Video

A novel loss (CoBi) for slightly misalighned image-to-image translation.

Zoom to Learn, Learn to Zoom

Xuaner Zhang, Qifeng Chen, Ren Ng, and Vladlen Koltun

Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Project Website

Supplement

3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis

Xiaojuan Qi*, Zhengzhe Liu*, Qifeng Chen, and Jiaya Jia

Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Supplementary Video

Send an email to Xiaojuan or me for the source code.

Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search

Zhuwen Li, Qifeng Chen, and Vladlen Koltun

Conference on Neural Information Processing Systems (NeurIPS), 2018

Source code

Semi-parametric Image Synthesis

Xiaojuan Qi, Qifeng Chen, Jiaya Jia, and Vladlen Koltun

Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Full Oral Presentation (2.1% acceptance rate)

Code and data

Demo Video

Interactive Image Segmentation with Latent Diversity

Zhuwen Li, Qifeng Chen, and Vladlen Koltun

Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Source code

Single Image Reflection Separation with Perceptual Losses

Xuaner Zhang, Ren Ng, and Qifeng Chen

Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Supplementary Material

Source code

Learning to See in the Dark

Chen Chen, Qifeng Chen, Jia Xu, and Vladlen Koltun

Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Project website

Speech Denoising with Deep Feature Losses

Francois G Germain, Qifeng Chen, and Vladlen Koltun

Interspeech 2019

arXiv preprint arXiv:1806.10522

Source Code

Project Website

Photographic Image Synthesis with Cascaded Refinement Networks

Qifeng Chen and Vladlen Koltun

International Conference on Computer Vision (ICCV), 2017

Full Oral Presentation (2.1% acceptance rate)

Project website

Fast Image Processing with Fully-Convolutional Networks

Qifeng Chen*, Jia Xu*, and Vladlen Koltun

International Conference on Computer Vision (ICCV), 2017

Project website

Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids

Qifeng Chen and Vladlen Koltun

Conference on Computer Vision and Pattern Recognition (CVPR), 2016

Full Oral Presentation (3.9% acceptance rate)

Project website (with source code)

Dense Monocular Depth Estimation in Complex Dynamic Scenes

René Ranftl, Vibhav Vineet, Qifeng Chen, and Vladlen Koltun

Conference on Computer Vision and Pattern Recognition (CVPR), 2016

Robust Nonrigid Registration by Convex Optimization

Qifeng Chen and Vladlen Koltun

International Conference on Computer Vision (ICCV), 2015

Full Oral Presentation (3.3% acceptance rate)

Project website (with Matlab source code)

Fast MRF Optimization with Application to Depth Reconstruction

Qifeng Chen and Vladlen Koltun

Conference on Computer Vision and Pattern Recognition (CVPR), 2014

Project website (with C++ and Matlab source code)

A Simple Model for Intrinsic Image Decomposition with Depth Cues

Qifeng Chen and Vladlen Koltun

International Conference on Computer Vision (ICCV), 2013

Matlab source code (updated on 2 Dec 2015)
Supplementary material   Poster

Please email to sintel@tue.mpg.de for the MPI Sintel dataset.

Motion-Aware KNN Laplacian for Video Matting

Dingzeyu Li, Qifeng Chen, and Chi-Keung Tang

International Conference on Computer Vision (ICCV), 2013

Project website

KNN Matting (with extension to layer color estimation)

Qifeng Chen, Dingzeyu Li, and Chi-Keung Tang

Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2013

Matlab source code (for layer color estimation)

KNN Matting

Qifeng Chen, Dingzeyu Li, and Chi-Keung Tang

Conference on Computer Vision and Pattern Recognition (CVPR), 2012

Project website (with Matlab source code)