andyzeng/tsdf-fusion-python

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1430 stars · 236 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A lightweight Python script that fuses multiple registered RGB-D images into a projective TSDF voxel volume, from which high-quality 3D surface meshes and point clouds can be extracted. It supports optional NVIDIA GPU acceleration via PyCUDA and is part of the 3DMatch toolbox.

Use cases

• fuse multiple RGB-D images into a TSDF voxel volume
• reconstruct a 3D mesh from depth camera frames
• generate point clouds from registered color and depth images
• preprocess volumetric data for 3D deep learning
• run KinectFusion-style TSDF fusion in Python
• convert depth image sequences into 3D surface models

When to choose

• you need a simple, scriptable TSDF fusion pipeline in Python
• you have registered RGB-D images with known camera poses
• you want GPU-accelerated volumetric fusion on an NVIDIA GPU
• you're preparing voxel volumes for 3D deep learning research

When to avoid

• you need real-time SLAM or camera tracking built in
• you don't have depth/RGB-D data or camera poses
• you need a maintained library with active support
• you need CPU-only performance at high frame rates

Facets

library · maturity maintenance

image-processing computer-vision graphics gpu-computing computer-vision graphics machine-learning robotics python tsdf rgbd 3d-reconstruction depth-camera voxel-volume kinect-fusion mesh-generation point-cloud linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="andyzeng/tsdf-fusion-python")