a collection of efficient and precise numerical algorithms and operations with focus on linear algebra and computational geometry.

[NeurIPS 2024] DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos

PanoVLM: Low-Cost and Accurate Panoramic Vision and LiDAR Fused Mapping

A curated list of awesome Deep Stereo Matching resources

Fork of official source code repository for the calibre ebook manager

Media server for comics/mangas/BDs/magazines/eBooks with API, OPDS and Kobo Sync support

The official source code repository for the calibre ebook manager

Custom implementation of Corrleation Module

Open-source Android/Desktop remake of Civ V

[CVPR 2024] Real-Time HDR Video Reconstruction

Official code repository for the paper: "Neural Spline Fields for Burst Image Fusion and Layer Separation"

A library for efficient similarity search and clustering of dense vectors.

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (CVPR 2019)

Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes

[CVPR 2024] 4K4D: Real-Time 4D View Synthesis at 4K Resolution

Official Implementation of CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

Training library for local feature detection and matching

A scikit-learn compatible neural network library that wraps PyTorch

Tdarr - Distributed transcode automation using FFmpeg/HandBrake + Audio/Video library analytics + video health checking (Windows, macOS, Linux & Docker)

Implementation of DynIBaR Neural Dynamic Image-Based Rendering (CVPR 2023)

CubeSLAM: Monocular 3D Object Detection and SLAM

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

[CVPR 2023 Highlight] The Official Code for High-Frequency Stereo Matching Network

A library for differentiable robotics.

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

The 1st Place Solution of the Facebook AI Image Similarity Challenge (ISC21) : Descriptor Track.

It's React, but in Python

HomE: Homography-Equivariant Video Representation Learning