Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning solution of the NTIRE 2023 Image Shadow Removal Challenge.

Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

A collection of awesome text-to-image generation studies.

Fine-tune VAE of Stable Diffusion model

Code for project DS-Fusion

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

[CVPR 2024] Official code release of our paper "Diff-Plugin: Revitalizing Details for Diffusion-based Low-level tasks"

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Dual Diffusion Implicit Bridges for Image-to-Image Translation. ICLR 2023.

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

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)

Paint by Example: Exemplar-based Image Editing with Diffusion Models

[TPAMI 2024] Official PyTorch implementation of A Diffusion Model Translator for Efficient Image-to-Image Translation

Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models

This is an LWIR stereo-hyperspectral database to develop HADAR algorithms for thermal navigation. Based on this database, one can develop algorithms for TeX decomposition to generate TeX vision. On…

[CVPR'2024] Official implementation of the paper "ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation"

We propose a novel fusion strategy that can effectively fuse information from different modality combinations. We also propose a new model named Multi-Modal Segmentation TransFormer (MMSFormer) tha…

KAIST Multispectral Pedestrian Detection Benchmark [CVPR '15]

Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection, ICCV, 2019

This is an official implimentation of D2Styler

A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Era of Deep Learning (Awesome & Benchmark)

Official implementation of ICCV 2023 Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.

本项目是对《Neural Networks from Scratch in Python》读后的总结，在本项目中将应用Python（numpy）从0开始实现一个全连接神经网络，提供所有可运行代码，并对每一段代码加入注释（自己的理解）。本项目内容包括：全连接层、激活函数、损失函数、梯度、反向传播、优化器、正则化、dropout、数据集处理、模型验证、参数保存和下载、预测推理。

CVPR 2024 Official Repository

[CVPRW 2023] Offical Repo of "Few-Shot Depth Completion Using Denoising Diffusion Probabilistic Model"