bronemos/view-fusion
Official implementation of ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis
This project helps 3D artists, designers, or product visualizers create new perspectives of 3D objects from a limited set of existing images. You provide multiple unordered pictures of an object from different angles, and it generates a new image of that object from a specified, novel viewpoint. This is ideal for quickly visualizing products or models without needing a full 3D rendering pipeline.
No commits in the last 6 months.
Use this if you need to generate high-quality images of a 3D object from viewpoints you haven't photographed or rendered before, using just a few existing photos.
Not ideal if you require extremely precise 3D model reconstruction or only have a single image of your object without any additional contextual data.
Stars
36
Forks
2
Language
Python
License
MIT
Category
Last pushed
May 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bronemos/view-fusion"
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)