8 citations · 37 across the 10 of their papers we have counts for
7 papers · 1 filter
SwinFSR: Stereo Image Super-Resolution using SwinIR and Frequency Domain Knowledge
Ke Chen, Liangyan Li, Huan Liu +3
Stereo Image Super-Resolution (stereoSR) has attracted significant attention in recent years due to the extensive deployment of dual cameras in mobile phones, autonomous vehicles a…
A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformer
Yangyi Liu, Huan Liu, Liangyan Li +2
Recent years have witnessed an increased interest in image dehazing. Many deep learning methods have been proposed to tackle this challenge, and have made significant accomplishmen…
Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank
Shirui Huang, Keyan Wang, Huan Liu +2
Despite the remarkable achievement of recent underwater image restoration techniques, the lack of labeled data has become a major hurdle for further progress. In this work, we prop…
Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022
Li Gu, Zhixiang Chi, Huan Liu +2
In this work, we present the winning solution for ORBIT Few-Shot Video Object Recognition Challenge 2022. Built upon the ProtoNet baseline, the performance of our method is improve…
Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
Huan Liu, Li Gu, Zhixiang Chi +4
Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep learning system to incrementally learn new classes with limited data. Recently, a pioneer clai…
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
Yawei Li, Kai Zhang, Radu Timofte +108
This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-reso…
Pseudo Supervised Monocular Depth Estimation with Teacher-Student Network
Huan Liu, Junsong Yuan, Chen Wang +1
Despite recent improvement of supervised monocular depth estimation, the lack of high quality pixel-wise ground truth annotations has become a major hurdle for further progress. In…