RahulSajnani/GeoDiffuser
[WACV 2025, Best Student Paper, Oral] GeoDiffuser: Geometry-Based Image Editing with Diffusion Models
This tool helps graphic designers, marketers, and artists precisely edit objects within existing images. You provide an image and specify geometric changes like moving, rotating in 3D, or removing objects. It then generates a new, photorealistic image with the edits seamlessly integrated, including accurate lighting and shadows, even filling in areas where objects were removed.
No commits in the last 6 months.
Use this if you need to perform specific geometric transformations on objects within images, such as repositioning a product or virtually rotating an item, while maintaining photorealism.
Not ideal if you're looking for text-based image generation from scratch or general artistic style transfer without precise geometric control.
Stars
22
Forks
2
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Mar 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RahulSajnani/GeoDiffuser"
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...