VinAIResearch/LeMul

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)

34
/ 100
Emerging

This project helps researchers and developers reconstruct the 3D shape and texture of objects from a single image. By analyzing multiple images of the same object type (like faces or cats), it learns to infer a detailed 3D model, outputting realistic 3D representations. It's ideal for those working in computer vision research, 3D content creation, or visual effects.

No commits in the last 6 months.

Use this if you need to create realistic 3D models from 2D images, especially for object categories where many example images exist.

Not ideal if you need to reconstruct arbitrary, unique objects without a large dataset of similar items for training, or if you require real-time 3D scanning from a single image without prior learning.

3D-reconstruction computer-vision image-processing virtual-reality visual-effects
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

52

Forks

5

Language

Python

License

BSD-3-Clause

Last pushed

Nov 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/VinAIResearch/LeMul"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.