kkaiwwana/MVPbev
[ACM MM24 Poster] Official implementation of paper "MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability"
This project helps generate realistic, multi-angle street-view images from a bird's-eye-view (BEV) map and a text description. You provide a top-down semantic map and a prompt (e.g., "a red car driving on a sunny street"), and it outputs several consistent images from different camera perspectives. This is ideal for urban planners, autonomous vehicle developers, or virtual environment designers needing to visualize street scenes.
No commits in the last 6 months.
Use this if you need to create diverse, photorealistic street-level images with consistent views from a conceptual top-down layout and descriptive text.
Not ideal if you need a simple, ready-to-use application for image generation without deep technical setup or access to large datasets like NuScenes.
Stars
20
Forks
4
Language
Python
License
—
Category
Last pushed
Sep 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kkaiwwana/MVPbev"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
anchen1011/toflow
TOFlow: Video Enhancement with Task-Oriented Flow
NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and...
RuojinCai/doppelgangers
Doppelgangers: Learning to Disambiguate Images of Similar Structures
cvg/GlueStick
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
microsoft/SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)