divyakraman/HawkI2024
Codebase for the paper HawkI: HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View
This project helps generate an aerial or bird's-eye view of a scene from a single standard photograph. You provide one ground-level image and get back a new image showing that same scene as if viewed from above, optionally guided by a text description. This is useful for urban planners, architects, or even event organizers who need to visualize layouts or areas from a top-down perspective without needing complex 3D models or actual drone footage.
No commits in the last 6 months.
Use this if you need to quickly visualize a ground-level scene from an aerial perspective or generate various text-controlled viewpoints from a single image.
Not ideal if you require precise, photorealistic aerial imagery for surveying or detailed mapping, as this is a generative synthesis tool.
Stars
13
Forks
3
Language
Python
License
—
Category
Last pushed
Jun 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/divyakraman/HawkI2024"
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...