Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Python sample codes and textbook for robotics algorithms.

State-of-the-art 2D and 3D Face Analysis Project

Image augmentation for machine learning experiments.

StyleGAN - Official TensorFlow Implementation

A collaboration friendly studio for NeRFs

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

Infinite Photorealistic Worlds using Procedural Generation

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8…

Visual localization made easy with hloc

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

A procedural Blender pipeline for photorealistic training image generation

Advancing Open-source World Models

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia, Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Dimensional is the agentic operating system for physical space. Vibecode humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seam…

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

A Unified Framework for Surface Reconstruction

SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

Deep Hough Voting for 3D Object Detection in Point Clouds

Learning Continuous Signed Distance Functions for Shape Representation

A trusty face analysis research platform developed by Tencent Youtu Lab

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

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation