CompVis/geometry-free-view-synthesis
Is a geometric model required to synthesize novel views from a single image?
This tool helps architects, real estate agents, or urban planners create virtual walkthroughs or explore different perspectives of a scene from just a single photograph. You provide one image of an indoor or outdoor space, and it generates new views as if you're moving through the scene. This is ideal for quickly visualizing how a space looks from various angles without needing complex 3D modeling.
379 stars. No commits in the last 6 months.
Use this if you need to generate multiple realistic views of a physical space from a single input image, allowing for interactive exploration or video creation.
Not ideal if you require precise 3D measurements, object manipulation within the scene, or highly accurate geometric reconstruction.
Stars
379
Forks
34
Language
Python
License
MIT
Category
Last pushed
Apr 16, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CompVis/geometry-free-view-synthesis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
kyegomez/Gamba
Implementation of PyTorch: "GAMBA: MARRY GAUSSIAN SPLATTING WITH MAMBA FOR SINGLE-VIEW 3D RECONSTRUCTION"
perceivelab/trf-sg2im
Official PyTorch implementation of the paper Transformer-Based Image Generation from Scene...
tthinking/DATFuse
[IEEE TCSVT 2023] Official implementation of DATFuse: Infrared and Visible Image Fusion via Dual...
tthinking/YDTR
[IEEE TMM 2022] Official implementation of YDTR: Infrared and Visible Image Fusion via Y-shape...
miaodd98/ITrans-Generative-Image-Inpainting-with-Transformers-ChinaMM-2023-Multimedia-Systems
ITrans: Generative Image Inpainting with Transformers, ChinaMM 2023, Multimedia Systems