mohammadasim98/scenetok
[CVPR '26] SceneTok: A Compressed, Diffusable Token Space for 3D Scenes
This project helps researchers and developers working with 3D scenes to efficiently represent and generate them. It takes collections of 2D images (view sets) of a scene as input and condenses them into a compact, manageable 1D token representation. This compressed form can then be used to generate new views of the scene or create entirely new scenes, which is useful for tasks like virtual reality, architectural visualization, or robotics simulation.
124 stars.
Use this if you need to compress 3D scene data from multiple camera views into a smaller, more flexible format for easier manipulation, storage, or generation of new scene variations.
Not ideal if your primary goal is real-time interaction with complex 3D models or if you don't require generative capabilities for novel scene views.
Stars
124
Forks
4
Language
Python
License
MIT
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mohammadasim98/scenetok"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...