Shuaicheng LIU, Ph.D.
Professor
School of Information and Communication Engineering
University of Electronic Science and Technology of China
Address: 2006 Xiyuan Ave, Chengdu, Sichuan, China. 611731.
[Google Scholar] [DBLP] [CV]
|
Shuaicheng LIU, Ph.D. Professor School of Information and Communication Engineering University of Electronic Science and Technology of China
Address: 2006 Xiyuan Ave, Chengdu, Sichuan, China. 611731. [Google Scholar] [DBLP] [CV]
|
|---|
| Short Bio |
Shuaicheng Liu is a Professor at School of Information and Communication Engineering, University of Electronic Science and Technology of China, working on computer vision, computer graphics and computational imaging, with applications in mobile photography and videography. He received his Ph.D degree at Electrical & Computer Engineering, supervised by Prof. Ping Tan in 2014 and received his Master degree at School of Computing,supervised by Prof. Michael S.Brown, in 2010, both from National University of Singapore. He obtained his Bachelor degree in Sichuan University in 2008. He joined the group of Prof. Bing Zeng at UESTC in 2014. During the internship, he was luckily mentored by Dr. Jian Sun, Dr. Lu Yuan at Microsoft Research and Dr. Jue Wang, Dr. Sunghyun Cho at Adobe. |
| Teaching |
|
|
| Selected Publications | |
| 2024 | |
 |
DMHomo: Learning Homography with Diffusion Models |
 |
Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond |
 |
GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning |
 |
You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection |
 |
Neural Spectral Decomposition for Dataset Distillation |
 |
Eliminating Warping Shakes for Unsupervised Online Video Stitching |
 |
LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models |
 |
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval |
 |
PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training |
 |
FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models |
 |
Efficient Meshflow and Optical Flow Estimation from Event Cameras |
 |
RecDiffusion: Rectangling for Image Stitching with Diffusion Models |
 |
HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions |
 |
Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation |
 |
SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field |
2023 |
|
 |
Low-Light Image Enhancement with Wavelet-based Diffusion Models |
 |
Unsupervised Global and Local Homography Estimation with Motion Basis Learning |
 |
Deep Homography Mixture for Single Image Rolling Shutter Correction |
 |
Minimum Latency Deep Online Video Stabilization |
 |
Supervised Homography Learning with Realistic Dataset Generation |
 |
MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion |
 |
Learning Optical Flow from Event Camera with Rendered Dataset |
 |
SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration |
 |
Parallax-Tolerant Unsupervised Deep Image Stitching |
 |
Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network |
 |
Explicit Motion Disentangling for Efficient Optical Flow Estimation |
 |
GAFlow: Incorporating Gaussian Attention into Optical Flow |
 |
AccFlow: Backward Accumulation for Long-Range Optical Flow |
 |
Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching |
 |
DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution |
 |
Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint |
2022 |
|
 |
Content-Aware Unsupervised Deep Homography Estimation and Its Extensions |
 |
D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution |
 |
Ghost-free High Dynamic Range Imaging with Context-aware Transformer |
 |
RealFlow: EM-based Realistic Optical Flow Datasets Generation from Videos |
 |
MIPI 2022 Challenge on RGBW Sensor Fusion: Dataset and Report |
 |
BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment |
 |
Learning Optical Flow with Kernel Patch Attention |
 |
Unsupervised Homography Estimation with Coplanarity-Aware GAN |
 |
Learning to Zoom Inside Camera Imaging Pipeline |
 |
Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer |
 |
Deep Rectangling for Image Stitching: A Learning Baseline |
 |
Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation |
 |
SceneSqueezer: Learning to Compress Scene for Camera Relocalization |
 |
Deep Constrained Least Squares for Blind Image Super-Resolution |
 |
RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging |
 |
FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration |
 |
Learning Optical Flow with Adaptive Graph Reasoning |
2021 |
|
|
Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection |
 |
DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization |
 |
OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration |
|
GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning |
 |
GLM-Net : Global and Local Motion Estimation via Task-Oriented Encoder-Decoder Structure |
 |
ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging |
 |
EBSR: Feature Enhanced Burst Super-Resolution with Deformable Alignment |
 |
UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning |
 |
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection |
 |
Holistic 3D Scene Understanding from a Single Image with Implicit Representation |
 |
Practical Wide-Angle Portraits Correction with Deep Structured Models |
2020 and before |
|
|
Content-Aware Unsupervised Deep Homography Estimation (Oral presentation) |
 |
DaST: Data-free Substitute Training for Adversarial Attacks (Oral presentation) |
 |
Neural Point Cloud Rendering via Multi-Plane Projection |
 |
Multi-exposure photomontage with hand-held cameras Ru Li, Shuaicheng Liu, Guanghui Liu, Tiecheng Sun, Jishun Guo. Computer Vision and Image Understanding (CVIU), vol. 193, pp. 102929, 2020. [PDF] [BibTex] |
 |
C3AE:Exploring the Limits of Compact Model for Age Estimation |
 |
DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image |
 |
Direct Photometric Alignment by Mesh Deformation |
 |
MeshFlow: Minimum Latency Online Video Stabilization |
 |
Automatic Reflection Removal using Gradient Intensity and Motion Cues |
 |
SteadyFlow: Spatially Smooth Optical Flow for Video Stabilization |
 |
TrackCam: 3D-aware Tracking Shots from Consumer Video Shuaicheng Liu,Jue Wang, Sunghyun Cho, Ping Tan. ACM Transactions on Graphics (SIGGRAPH asia). 2014 [PDF] [Project Page] [YouTube] [Video(34 MB)] [BibTex] |
 |
Bundled Camera Paths for Video Stabilization. (Product Transfer: Blink app) Shuaicheng Liu,Lu Yuan,Ping Tan,Jian Sun. ACM Transactions on Graphics (SIGGRAPH). 2013 [PDF] [Project Page] [YouTube] [Video(66 MB)] [Data Page] [BibTex] |
 |
Video Stabilization with a Depth Camera Shuaicheng Liu,Yinting Wang,Lu Yuan,Jiajun Bu,Ping Tan,Jian Sun. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2012 [PDF] [Project Page] [BibTex] |
 |
Colorization for Single Image Super Resolution |
 |
Super Resolution using Edge Prior and Single Image Detail Synthesis Yu-Wing Tai,Shuaicheng Liu,Michael S.Brown,Stephen Lin. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2010 [PDF] [Project Page] [Code] [BibTex] |
| Last Update: Dec., 2024. @2024. All Rights Reserved. |
