divyakraman/AerialDiffusion
Codebase for the paper Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models
This tool transforms a standard ground-level photograph into an aerial view, guided by your text description. You provide a single ground-view image and a text prompt (e.g., "a forest with a river"), and it generates an overhead perspective. This is ideal for urban planners, landscape architects, or environmental analysts who need to visualize areas from a bird's-eye view.
No commits in the last 6 months.
Use this if you need to quickly generate an aerial perspective of a scene when only ground-level photos are available and you want to control the output with descriptive text.
Not ideal if you require precise, photogrammetry-grade aerial mapping or need to generate views from specific camera angles other than directly overhead.
Stars
13
Forks
2
Language
Python
License
—
Category
Last pushed
Oct 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/divyakraman/AerialDiffusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation