Yukun-Huang/DreamCube
[ICCV 2025] Official implementation of the paper "DreamCube: 3D Panorama Generation via Multi-plane Synchronization".
This project helps 3D artists and virtual environment designers generate immersive 3D scenes and panoramas from a single image. You provide a single photograph, and it outputs a complete 360-degree panoramic image with depth information, as well as a 3D scene representation like a mesh or 3D Gaussian Splatting model. This tool is ideal for creators working in virtual reality, game design, or architectural visualization.
173 stars.
Use this if you need to quickly transform a single 2D image into a full 3D environment or a detailed 360-degree panoramic view.
Not ideal if you require hyper-realistic, photogrammetry-level accuracy for highly detailed real-world scene reconstruction.
Stars
173
Forks
11
Language
Python
License
—
Category
Last pushed
Feb 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Yukun-Huang/DreamCube"
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...