+
Skip to content
@3DTopia

3D Topia

README.md

3D Topia

Welcome to the 3D Topia homepage. 3D Topia is mainly developed by Shanghai AI Laboratory. We keep working in the field of versatile 3D content generation, open-sourcing the datasets, the models, and benchmark suites.

GitHub User's stars

🚀 Updates

🔥 3DTopia-XL

  • [09/2024] We release 3DTopia-XL, a high-quality 3D generative model with 1 billion parameters, which supports the generation of 3D assets with high-resolution geometry, texture, and material into GLB format.

🔥 3DTopia

  • [03/2024] Technical report of 3DTopia is released.
  • [01/2024] We release 3DTopia, a two-stage text-to-3D generation model that uses hybrid diffusion priors for high quality 3D assets generation.

🍿 Datasets

🎁 Models

  • 🎉 [new] 3DTopia-XL: Comming soon...
  • LGM: Large Multi-View Gaussian Model for high-resolution 3D content creation from text prompts or images.
  • 3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors

🏔️ Bench

  • 3DGen-Arena: Human preference for text-to-3D and image-to-3D generative models.
  • GPTEval3D: GPT-4V(ision) is a human-aligned evaluator for text-to-3D generation.

Popular repositories Loading

  1. LGM LGM Public

    [ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

    Python 1.9k 129

  2. OpenLRM OpenLRM Public

    An open-source impl. of Large Reconstruction Models

    Python 1.1k 64

  3. 3DTopia-XL 3DTopia-XL Public

    [CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

    Python 991 36

  4. 3DTopia 3DTopia Public

    Text-to-3D Generation within 5 Minutes

    Python 712 49

  5. MaterialAnything MaterialAnything Public

    [CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion

    Python 297 13

  6. Phidias-Diffusion Phidias-Diffusion Public

    [ICLR 2025] Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

    Python 270 12

Repositories

Showing 10 of 17 repositories
  • MVPaint Public

    [CVPR 2025] MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D

    3DTopia/MVPaint’s past year of commit activity
    213 6 0 0 Updated Jul 8, 2025
  • GenDoP Public

    GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography

    3DTopia/GenDoP’s past year of commit activity
    Python 65 Apache-2.0 2 2 0 Updated Jul 3, 2025
  • DynamicCity Public

    [ICLR 2025 Spotlight] Official implementation for "DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes"

    3DTopia/DynamicCity’s past year of commit activity
    Python 201 8 0 0 Updated Jun 20, 2025
  • MaterialAnything Public

    [CVPR 2025 Highlight] Material Anything: Generating Materials for Any 3D Object via Diffusion

    3DTopia/MaterialAnything’s past year of commit activity
    Python 297 13 13 0 Updated Jun 10, 2025
  • LayerPano3D Public

    [SIGGRAPH 2025] LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation"

    3DTopia/LayerPano3D’s past year of commit activity
    Python 261 Apache-2.0 7 7 0 Updated May 14, 2025
  • Imagine360 Public

    Official code of "Imagine360: Immersive 360 Video Generation from Perspective Anchor"

    3DTopia/Imagine360’s past year of commit activity
    Python 131 Apache-2.0 6 1 0 Updated May 14, 2025
  • 3DTopia-XL Public

    [CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

    3DTopia/3DTopia-XL’s past year of commit activity
    Python 991 36 9 1 Updated May 7, 2025
  • Phidias-Diffusion Public

    [ICLR 2025] Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

    3DTopia/Phidias-Diffusion’s past year of commit activity
    Python 270 MIT 12 3 0 Updated Mar 4, 2025
  • Omni6D Public

    Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation

    3DTopia/Omni6D’s past year of commit activity
    Python 46 4 0 0 Updated Dec 11, 2024
  • GeneMAN Public

    GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

    3DTopia/GeneMAN’s past year of commit activity
    64 2 2 0 Updated Dec 3, 2024
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Python

Most used topics

Loading…
点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载