dreamgaussian/dreamgaussian

Health v2 · maintenance only

Adoption not part of the score

4352 stars · 399 forks observed · 2026-08-28

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

DreamGaussian is the official PyTorch implementation of an ICLR 2024 Oral paper for efficient 3D content creation using generative Gaussian Splatting. It generates textured 3D meshes from a single image or text prompt in about two minutes, roughly 10x faster than prior score-distillation methods.

Use cases

• generate a 3D model from a single photo
• create 3D assets from text prompts
• convert an image into a textured mesh for games
• rapid 3D prototyping from concept art
• research on 3D generative models and Gaussian splatting

When to choose

• you need fast image-to-3D or text-to-3D generation on a single consumer GPU
• you want exportable textured meshes rather than just radiance fields
• you are reproducing or building on published 3D generation research

When to avoid

• you need production-grade, artist-ready 3D assets with fine topology
• you lack a CUDA-capable GPU
• you need a polished end-user application rather than research code

Facets

library · maturity active

machine-learning deep-learning image-processing graphics stable-diffusion artificial-intelligence computer-vision graphics deep-learning windows python 3d-generation gaussian-splatting text-to-3d image-to-3d mesh-generation research-code iclr-2024 linux gpu

Member repositories

For agents

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