LinYark
Follow
Stars
《动手学大模型Dive into LLMs》系列编程实践教程
BokehMe: When Neural Rendering Meets Classical Rendering (CVPR 2022 Oral)
RealSee3D: A multi-view RGB-D dataset combining real-world captures and procedurally generated scenes, with extensible annotations for diverse 3D vision research.
[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
The state-of-the-art image restoration model without nonlinear activation functions.
[NeurIPS 2025] Pixel-Perfect Depth
[CVPR 2025 Highlight] All-directional Disparity Estimation for Real-world QPD Images
🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.
[ICCVW 2025] This repository includes latest papers, projects and datasets on GenAI for Cel-Animation. Accepted by ICCV 2025 AISTORY Workshop.
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
Local Light Field Synthesis (Pratul P. Srinivasan, Tongzhou Wang, Ashwin Sreelal, Ravi Ramamoorthi, Ren Ng ICCV 2017)
Resources for phase recovery (also called phase imaging, phase retrieval, or phase reconstruction)
Comprehensive optical design, optimization, and analysis in Python, including GPU-accelerated and differentiable ray tracing via PyTorch.
free finite-difference time-domain (FDTD) software for electromagnetic simulations
Differentiable geometric optics in PyTorch. Design optical systems with optimization.
[ICCV 2025] Official code for the paper "Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation"
Collect super-resolution related papers, data, repositories
记录近期的 1) 图像/视频的超分增强等low level vision任务; 2) 图像生成 等任务相关论文, 主要为18年以后的DL based方法.
A curated list of resources for Image and Video Deblurring
Official implementation of ICCV 2023 Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery
This is the open source repository for our IEEE Transactions on Computational Imaging 2022 paper "dO: A differentiable engine for Deep Lens design of computational imaging systems".
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Reference github repository for the paper "Defocus Deblurring Using Dual-Pixel Data". We introduce a deep neural network (DNN) architecture that uses the dual-pixel (DP) sub-aperture views to reduc…