Multiview Photometric Stereo (MVPS) Studio Hardware and Software for 3D Reconstruction

Local geometric features aggregation for robust point cloud registration

🎤 Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"

Cuda mesh utils.

Intel® Open Image Denoise library

SwinIR: Image Restoration Using Swin Transformer (official repository)

Code Release of MVInverse: Feedforward Multi-view Inverse Rendering in Seconds

[CVPR2019] The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

Visual Inertial Odometry with SLAM capabilities and 3D Mesh generation.

A fast and robust point cloud registration library

cuML - RAPIDS Machine Learning Library

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

Code accompanying paper "SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation"

[ICCV 2025] Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation

Atom3d, atomising geometry, is a mesh processing toolbox specifically designed for 3D learning.

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

Sharp Monocular View Synthesis in Less Than a Second

This is a cross-platform command-line tool for 3DGS(3D Gaussian Splatting), supporting conversions like ply to splat, ply to spx, ply to spz, ply to sog, and vice versa.

[ECCV 2024] "BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting". ⚡Train a scene from real-world blurry images in minutes!

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

News: the 10k dataset is ready for download.

[SIGGRAPH 2025 (Journal Track)] Facial Appearance Capture at Home with Patch-Level Reflectance Prior.

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".

Collect and summarize point cloud sota methods.

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.