caiyuanhao1998 Goto Github PK

followers: 390.0 following: 42.0 repos: 72.0 gists: 0.0

Name: Yuanhao Cai

Type: User

Company: Johns Hopkins University <- Tsinghua

Bio: Johns Hopkins University [email protected] [email protected]

Location: Baltimore, United States

Blog: https://caiyuanhao1998.github.io/

Yuanhao Cai

🚀 Interested in 3D Vision, Human Pose Estimation, Image Restoration, and Generative Adversarial Networks.

🎓 Now a first-year CS PhD student in Johns Hopkins University, advised by prof. Alan Yuille.

🔥 Obtained my BSE and MSE degrees from Tsinghua University in 2020 and 2023.

⚡ An active player in competitions of international top academic conferences:

🌱 My Repositories

Topic	Title	Badge
3D Reconstruction, Novel View Synthesis, and Volume Density Rendering	"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024)
Human Pose Estimation	"Learning Delicate Local Representations for Multi-Person Pose Estimation" (ECCV 2020 Spotlight) and "Res-Steps-Net for Multi-Person Pose Estimation" (ICCVW 2019 Best Paper Award & COCO 2019 Keypoint Challenge Winner)
Hypersepctral Image Reconstruction in Snapshot Compressive Imaging	"A toolbox for spectral compressive imaging reconstruction including our MST (CVPR 2022), CST (ECCV 2022), DAUHST (NeurIPS 2022), HDNet (CVPR 2022), MST++ (CVPRW 2022), etc."
Low-light Image Enhancement	"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023 & NTIRE 2024 First Runner-Up Award)
Hypersepctral Image Reconstruction from Single RGB Images	"MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction" (CVPRW 2022) & (Winner of NTIRE 2022 Challenge on Spectral Reconstruction from RGB)
Binarized Neural Network for Spectral Compressive Imaging Reconstruction	"Binarized Spectral Compressive Imaging" (NeurIPS 2023)
Real-world Noise Modelling and Removal	"Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training" (NeurIPS 2021)
Video Restoration	"A toolbox for video restoration (deblurring, super-resolution, and compressed video enhancedment) including our FGST (ICML 2022) and S2SVR (ICML 2022), and so on"
Medical Image Enhancement	"RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark" (J-BHI 2022)

Yuanhao Cai's Projects

3d_heart_pca

3dmppe_posenet_release

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image ", ICCV 2019

awesome-lifescience

A collection of awesome things regarding the LifeScience.

awesome-vision-attentions

Summary of related papers on visual attention

badges

:flower_playing_cards: Standard and acceptable badges list

bisci

A Toolbox for Binarized Spectral Compressive Imaging (NeurIPS 2023)

bmvctemplate

Paper template and author instructions for BMVC

caiyuanhao1998

caiyuanhao1998.github.io

Yuanhao Cai's Homepage

coding_note

cpptrace

A logging library to trace C++ variables.

cszn

dan

This is an official implementation of Unfolding the Alternating Optimization for Blind Super Resolution

darknet

YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )

deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

deephuman

Code for our ICCV paper "DeepHuman: 3D Human Reconstruction from a Single Image"

draw_script

dwpose

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

edsr-pytorch

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

essential

Essential 是一款以Vue3 + ts + vite + Element plus + EChart 5开发的快速页面生成组件库，开发快速，易于维护，不需要写过多的view层，只需要通过JSON + Js代码便可实现Element plus、EChart 5等所有组件。👉 ESSENTIAL 官方文档: http://essential.baic-mfexpress.com