snap-research/R2L
[ECCV 2022] R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis
This project helps 3D artists, game developers, or virtual reality creators generate new views of complex 3D scenes from a limited set of existing images. It takes a collection of photos of an object or scene as input and produces a compact digital representation that allows for rendering high-quality, realistic new perspectives much faster and with better visual fidelity than previous methods. This is ideal for those who need to create immersive virtual experiences or generate detailed 3D models efficiently.
191 stars. No commits in the last 6 months.
Use this if you need to render new, high-quality views of a 3D object or scene quickly from a few existing images, and require a compact digital representation for easier sharing or deployment.
Not ideal if you are looking for a simple, out-of-the-box solution without any programming or deep learning setup.
Stars
191
Forks
24
Language
Python
License
—
Category
Last pushed
Aug 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/snap-research/R2L"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
nerfstudio-project/nerfstudio
A collaboration friendly studio for NeRFs
google/nerfies
This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.
SuLvXiangXin/zipnerf-pytorch
Unofficial implementation of ZipNeRF
google/hypernerf
Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural...