nv-tlabs/GET3D

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

4435 stars · 408 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

GET3D is NVIDIA's PyTorch implementation of a generative model that synthesizes high-quality 3D textured meshes (cars, chairs, animals, buildings) directly from 2D image collections. It combines differentiable surface modeling and rendering with 2D GANs to produce meshes usable in standard 3D rendering engines.

Use cases

• generate 3d textured meshes from images
• create 3d assets for game engines automatically
• train a 3d generative model on a 2d image dataset
• generate procedural 3d content like cars and buildings
• research 3d gan and differentiable rendering methods

When to choose

• you need to generate diverse, textured 3D meshes for virtual worlds or games
• you have 2D image collections and want to learn a 3D generative model
• you want a research-grade baseline for 3D GANs with pretrained Shapenet models

When to avoid

• you lack high-end NVIDIA GPUs (V100/A100 recommended)
• you need production-supported software rather than a research codebase
• you need interactive 3D modeling rather than automated generation

Facets

library · maturity maintenance

machine-learning deep-learning image-processing graphics simulation deep-learning computer-vision graphics artificial-intelligence python generative-model 3d-mesh-generation gan textured-meshes pytorch research-code differentiable-rendering neurips-2022 linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nv-tlabs/GET3D")