Contexts Optical Compression

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Universal Monocular Metric Depth Estimation

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

RainSense: An Autonomous Driving Environmental Perception Dataset with Rain Intensity Labels

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian

[CVPR 2025 Oral & Award Candidate] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

CUDA accelerated rasterization of gaussian splatting

A conda-forge distribution.

The Fast Cross-Platform Package Manager

Visual localization made easy with hloc

open Multi-View Stereo reconstruction library

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

The open source mesh processing system

Some plugins for highD series dataset

Grounding Image Matching in 3D with MASt3R

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

CoTracker is a model for tracking any point (pixel) on a video.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Official implementation of On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images. A. Meuleman, I. Shah, A. Lanvin, B. Kerbl, G. Drettakis, ACM TOG (proc. SIGGRAPH) 2025

RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian

Ray tracing and hybrid rasterization of Gaussian particles

NVIDIA Isaac Sim™ is an open-source application on NVIDIA Omniverse for developing, simulating, and testing AI-driven robots in realistic virtual environments.

Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models

A PyTorch Library for Accelerating 3D Deep Learning Research