Xin Li's repositories
Awesome-diffusion-model-for-image-processing
one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment
GraphAdapter
The efficient tuning method for VLMs
KVQ-Challenge-CVPR-NTIRE2024
The first challenge on short-form video quality assessment
Causal-IR-DIL
Distortion invariant feature learning for image restoration from a causality perspective
Enhance-Anything
Enhance and restore any things continuously with Segment Anything
HST-for-Compressed-Image-SR
The code for AIM2022 compressed image super-resolution
SAMB-TransformerUDA
Semantic-adaptive Message Broadcasting for Transformer-based UDA
Task-driven-Semantic-Coding-via-RL
The code for our proposed Task-driven Semantic Coding via Reinforcement Learning in TIP2021
Openworld-IQA
The repo is devoted to develop the open-world IQA schemes.
Domain-generalization
All about domain generalization
Inpaint-Anything
Inpaint anything using Segment Anything and inpainting models.
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
UCIP.github.io
UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt