nianticlabs/diffusionerf

[CVPR 2023] DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models

38
/ 100
Emerging

This project helps computer vision researchers working with Neural Radiance Fields (NeRFs) create higher-quality 3D scene representations from a small number of 2D images. You input a collection of 2D images and their camera poses, and it outputs a more robust and visually consistent 3D NeRF model. Researchers studying 3D reconstruction and novel view synthesis will find this useful.

306 stars. No commits in the last 6 months.

Use this if you need to generate realistic 3D scenes or novel views from a limited set of input photographs and want to improve the robustness and detail of your NeRF models.

Not ideal if you are looking for a ready-to-use application for casual 3D modeling or don't have access to powerful GPU hardware.

3D Reconstruction Computer Vision Research Novel View Synthesis Neural Radiance Fields Scene Generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

306

Forks

17

Language

Python

License

MIT

Last pushed

Nov 23, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nianticlabs/diffusionerf"

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