Skip to content
View HarukiYqM's full-sized avatar

Highlights

  • Pro
Block or Report

Block or report HarukiYqM

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
HarukiYqM/README.md

About Me👋

Blog Badge Gmail Badge Linkedin Badge

🎵 Focusing on computer vision.

💬 Now PhD student at JHU. Obtained my bachelor's degree from UIUC

💌 Alumni of UIUC-IFP and SHI Lab

Research

I have developed a series of self-attention operations for image restoration:

Cross-Scale Non-Local Attention (CVPR20) [Paper] [Code]

Non-local Sparse Attention (CVPR21) [Paper] [Code]

Pyramid Attention Networks (IJCV23) [Paper] [Code]

Please feel free to check them.

Pinned

  1. pytorch-ZSSR pytorch-ZSSR Public

    Pytorch implementation of "Zero Shot" Super Resolution

    Python 57 14

  2. Non-Local-Sparse-Attention Non-Local-Sparse-Attention Public

    PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

    Python 174 19

  3. SHI-Labs/Pyramid-Attention-Networks SHI-Labs/Pyramid-Attention-Networks Public

    [IJCV] Pyramid Attention Networks for Image Restoration: new SOTA results on multiple image restoration tasks: denoising, demosaicing, compression artifact reduction, super-resolution

    Python 384 52

  4. SHI-Labs/Cross-Scale-Non-Local-Attention SHI-Labs/Cross-Scale-Non-Local-Attention Public

    PyTorch code for our paper "Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining" (CVPR2020).

    Python 400 46

  5. All-In-One-Neural-Composition All-In-One-Neural-Composition Public

    PyTorch code for our paper "Resource-Adaptive Federated Learning with All-In-One Neural Composition" (NeurIPS2022)

    Python 15 1