nywang16/Pixel2Mesh

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1765 stars · 305 forks observed · 2026-08-28

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

Pixel2Mesh is the official TensorFlow implementation of the ECCV 2018 paper that generates 3D mesh models from a single RGB image using a graph convolutional encoder-decoder. It includes pre-trained models, a demo script, and CUDA implementations of Chamfer Distance and Earth Mover's Distance for training and evaluation.

Use cases

• reconstruct a 3d mesh from a single photo
• generate 3d models from rgb images
• run pixel2mesh demo on a picture
• train a single-image 3d reconstruction model
• evaluate 3d shape reconstruction with chamfer distance and emd
• convert an image of an object into an obj mesh file

When to choose

• you need to reproduce or build on the ECCV 2018 Pixel2Mesh paper
• you want a pre-trained model to turn single images into 3D meshes
• you need CUDA implementations of CD and EMD loss metrics for point cloud research

When to avoid

• you need a maintained production-ready library - the code targets Python 2.7 and TensorFlow 1.x
• you want multi-view or video-based 3D reconstruction
• you lack a CUDA-enabled GPU

Facets

library · maturity maintenance

machine-learning deep-learning image-processing graphics simulation computer-vision machine-learning deep-learning graphics artificial-intelligence python 3d-reconstruction mesh-generation single-image tensorflow eccv2018 shapenet research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nywang16/Pixel2Mesh")