⏬ Dumb downloader that scrapes the web

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Graph Neural Network Library for PyTorch

🐍 Geometric Computer Vision Library for Spatial AI

Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

DUSt3R: Geometric 3D Vision Made Easy

Game Boy emulator written in Python

Background Matting: The World is Your Green Screen

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

Visual localization made easy with hloc

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

MVSNet (ECCV2018) & R-MVSNet (CVPR2019)

Python code to fuse multiple RGB-D images into a TSDF voxel volume.

Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"

Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

Direct voxel grid optimization for fast radiance field reconstruction.

Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)

[IJCV 2022] Bridging Composite and Real: Towards End-to-end Deep Image Matting

【CVPR 2025 Highlight】MonSter: Marry Monodepth to Stereo Unleashes Power

[TPAMI 2025 & CVPR 2023] Iterative Geometry Encoding Volume for Stereo Matching

MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

Pytorch implementation of our paper "CLRNet: Cross Layer Refinement Network for Lane Detection" (CVPR2022 Acceptance).

DeMoN: Depth and Motion Network