[CVPR'23] Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM

Open3D: A Modern Library for 3D Data Processing

Computer-vision dataset tools that I am using or working on

⚡ Dynamically generated stats for your github readmes

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Lightning fast C++/CUDA neural network framework

Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"

Real-time Neural Signed Distance Fields for Robot Perception

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

Atlas: End-to-End 3D Scene Reconstruction from Posed Images

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

Plenoxels: Radiance Fields without Neural Networks, Code release WIP

Download a large file from Google Drive (curl/wget fails because of the security notice).

DirectVoxGO reconstructs a scene representation from a set of calibrated images capturing the scene. We achieve NeRF-comparable novel-view synthesis quality with super-fast convergence.

Code release for NeuS

The implementation of "Bootstrapping Semantic Segmentation with Regional Contrast".

OpenMMLab's next-generation platform for general 3D object detection.

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects

Pangolin is a lightweight portable rapid development library for managing OpenGL display / interaction and abstracting video input.

Implementation of cv::Mat conversion to numpy.array for pybind11