yilundu/cross_attention_renderer

CVPR 2023: Learning to Render Novel Views from Wide-Baseline Stereo Pairs

29
/ 100
Experimental

This tool helps researchers and visual effects artists generate smooth video transitions or novel viewpoints between two photos taken from significantly different angles. You input two wide-baseline images, and it outputs a video or a series of images that realistically interpolates the space between those two original views. It's designed for anyone working with 3D reconstruction, virtual reality content, or cinematic effects.

152 stars. No commits in the last 6 months.

Use this if you need to create compelling visual narratives or 3D scene understanding from just two disparate images, without complex 3D modeling.

Not ideal if you require real-time rendering for interactive applications or if you only have a single image as input.

3D-reconstruction computer-vision-research visual-effects virtual-reality-content cinematography
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

152

Forks

11

Language

Python

License

Last pushed

Jan 05, 2024

Commits (30d)

0

Get this data via API

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

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