Shihao Zhou (周世豪)

I am a second-year PhD student at Nankai University where I am advised by Prof. Jufeng Yang. Before that, I completed my Master at Xiamen University and obtained my BS degree at Zhejiang Gongshang University.

I am very fortunate to be co-advised by Prof. Jinshan Pan of Nanjing University of Science and Technology.

I am interested in 3D Computer Vision and Low-level Vision problems.

Email  /  CV  /  Bio  /  Google Scholar  /  Github

profile photo
News

[Jul , 2024] FPro is accepted by ECCV 2024.

[Feb , 2024] AST is accepted by CVPR 2024.

Publications (Selected)
Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration
Shihao Zhou, Jinshan Pan, Jinglei Shi, Duosheng Chen, Lishen Qu, Jufeng Yang,
European Conference on Computer Vision (ECCV), 2024
project page / arXiv / bibtex

We develop a Frequency Prompting image restoration method, dubbed FPro, which can effectively provide prompt components from a frequency perspective to guild the restoration model.

Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration
Shihao Zhou, Duosheng Chen, Jinshan Pan, Jinglei Shi, Jufeng Yang,
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
project page / pdf / bibtex

We present AST, an efficient Transformer-based model, that facilitates the flow of the most useful information forward, extracting more constructive features for the recovery of clear images.

JSL3d: Joint subspace learning with implicit structure supervision for 3D pose estimation
Mengxi Jiang, Shihao Zhou, Cuihua Li, Yunqi Lei
Pattern Recognition (PR), 132(2022) 108965
project page / pdf / bibtex

A novel joint subspace learning approach with implicit structure supervision based on Sparse Representation (SR) model.

DC-GNet: Deep Mesh Relation Capturing Graph Convolution Network for 3D Human Shape Reconstruction
Shihao Zhou, Mengxi Jiang, Shanshan Cai, Yunqi Lei
ACM International Conference on Multimedia (MM), 2021   (Oral Presentation)
project page / poster / supplementary / arXiv / bibtex

Exploring deep relations within mesh vertices and proposing a shape completion task for human mesh reconstruction.

Towards Locality Similarity Preserving to 3D Human Pose Estimation
Shihao Zhou, Mengxi Jiang, Qicong Wang, Yunqi Lei
Asian Conference on Computer Vision (ACCV) Workshop, 2020
project page / pdf / bibtex

A simple example-based approach with locality similarity preserving to estimate 3D human pose.


‘Whether I shall turn out to be the hero of my own life,

or whether that station will be held by anybody else,

these pages must show ‘

This guy has an awesome website.