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

COMO: Compact Mapping and Odometry

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

Geometric Computer Vision Library for Spatial AI

GLOMAP - Global Structured-from-Motion Revisited

Grounding Image Matching in 3D with MASt3R

Implementation of the tree model published by Weber & Penn

Visualize streams of multimodal data. Free, fast, easy to use, and simple to integrate. Built in Rust.

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

Visual localization made easy with hloc

[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction

a programming library with geometric algorithms

Reproducible evaluation of NeRF and 3DGS methods

Distribute and run LLMs with a single file.

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

Official code for CVPR 2022 paper "Rethinking Visual Geo-localization for Large-Scale Applications"

Fast, efficient and accurate multi-resolution, multi-sensor 3D occupancy mapping

A procedural Blender pipeline for photorealistic training image generation

COLMAP - Structure-from-Motion and Multi-View Stereo

Python bindings for COLMAP

An iOS app that collects/streams posed images for NeRFs using ARKit

PLVS is a real-time SLAM system with points, lines, volumetric mapping and 3D unsupervised incremental segmentation.

The ultimate list of open data semantic 3D city models

BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

Algorithm to texture 3D reconstructions from multi-view stereo images

Official implementation for Tetra-NeRF paper - NeRF represented as triangulation of input point cloud.

Benchmark for visual localization on imperfect 3D mesh models from the Internet