Code to easily try 30 (and growing) different image matching methods

SAMPart3D: Segment Any Part in 3D Objects

[CVPR 2024 Highlight] Official repository for the paper "3DGStream: On-the-fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos".

[TVCG 2024] Official implementation of "JIMR: Joint Semantic and Geometry Learning for Point Scene Instance Mesh Reconstruction”

Blender add-on for editing scenes reconstructed with SuGaR or Gaussian Frosting.

A GPU implementation of Model Predictive Path Integral (MPPI) control that uses a probabilistic traversability model for planning risk-aware trajectories.

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

ASCII generator (image to text, image to image, video to video)

[BMVC 2024] Drone-assisted Road Gaussian Splatting with Cross-view Uncertainty

[NeurIPS 2024] Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis

CUDA accelerated rasterization of gaussian splatting

SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

WebGL 3D Gaussian Splat Viewer

Official PyTorch implementation of "UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video"

Official implementation of the paper "HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting""

Implementation of Reliable Feature-Line Driven Quad-Remeshing

Release repo for our SLAM Handbook

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching

Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

Model Predictive Path Integral (MPPI) with approximate dynamics implemented in pytorch

text2robot is an open-source project leveraging text-to-mesh generative models to create robotic designs, which are then optimized using evolutionary algorithms based on user-specified aesthetics a…

PyViz3D is a web-based visualizer for 3D objects and point clouds.

This is a collective repository for all 3DGS related progresses in research and industry world

🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

Postgraduate Thesis: fast_lio_sam + dynamic removal (T-GRS 2024) + multi-session mapping (ICRA 2022 Kim) + object-level update + online relocalization (ICRA 2025 submittion) + real-world applicatio…

🤗 image matching toolbox webui

LLM inference in C/C++

Extension and update of M2DGR: a novel Multi-modal and Multi-scenario SLAM Dataset for Ground Robots (ICRA2022 & ICRA2024)