Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).

List of papers related to neural network quantization in recent AI conferences and journals.

A Collection of Low Level Vision Research Groups

RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

[ACCV 2024] Official code of our paper "Joint Image Super-resolution and Low-light Enhancement in the Dark"

Sobel edge detection implemented on PyTorch

End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution

[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

My VitePress website I made to visually compare the output I created with over 600 different AI upscaling models. Running under https://phhofm.github.io/upscale/

Winner of runtime track in NTIRE 2022 challenge on Efficient Super-Resolution

A collection of awesome custom nodes for ComfyUI

for tile the image for advanced control or modification

comfyui节点文档插件,enjoy~~

FLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, SwarmUI, DeepFake, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, Comfy…

🎨ComfyUI standalone pack with 40+ custom nodes. | ComfyUI 大号整合包，预装大量自定义节点（不含SD模型）

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

CFA (Colour Filter Array) demosaicing algorithms for Python

A library to aid in using colors

Exploiting raw images for real-scene super-resolution, TPAMI 2021

[ECCV 2024] codes of DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023

PyTorch library for solving imaging inverse problems using deep learning

SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-Time Performance on Mobile Device, in ICCV 2023

This is the official implementation of "Deep-FlexISP: A Three-Stage Framework for Night Photography Rendering"

Learning Tone Curves for Local Image Enhancement

Learning Compressed Representation of 3DLUT for Image-enhancement. Higher performance with much smaller models! ☺️