25 citations · 61 across the 11 of their papers we have counts for
11 papers
FLAME-based Multi-View 3D Face Reconstruction
Wenzhuo Zheng, Junhao Zhao, Xiaohong Liu +4
At present, face 3D reconstruction has broad application prospects in various fields, but the research on it is still in the development stage. In this paper, we hope to achieve be…
AccFlow: Backward Accumulation for Long-Range Optical Flow
Guangyang Wu, Xiaohong Liu, Kunming Luo +6
Recent deep learning-based optical flow estimators have exhibited impressive performance in generating local flows between consecutive frames. However, the estimation of long-range…
FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table
Wenhao Li, Guangyang Wu, Wenyi Wang +2
Low-Light Video Enhancement (LLVE) has received considerable attention in recent years. One of the critical requirements of LLVE is inter-frame brightness consistency, which is ess…
StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability
Tengchuan Kou, Xiaohong Liu, Wei Sun +4
Video shakiness is an unpleasant distortion of User Generated Content (UGC) videos, which is usually caused by the unstable hold of cameras. In recent years, many video stabilizati…
RAWIW: RAW Image Watermarking Robust to ISP Pipeline
Kang Fu, Xiaohong Liu, Jun Jia +4
Invisible image watermarking is essential for image copyright protection. Compared to RGB images, RAW format images use a higher dynamic range to capture the radiometric characteri…
NTIRE 2023 Quality Assessment of Video Enhancement Challenge
Xiaohong Liu, Xiongkuo Min, Wei Sun +69
This paper reports on the NTIRE 2023 Quality Assessment of Video Enhancement Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement W…