cgtuebingen/SIGNeRF
SIGNeRF: Scene Integrated Generation for Neural Radiance Fields
This tool helps 3D artists, game developers, or architects easily modify existing 3D scenes. You provide a previously created Neural Radiance Field (NeRF) model and text descriptions or geometric guides. The tool then generates a new, altered 3D scene that incorporates your edits, offering a way to quickly iterate on visual designs without starting from scratch.
129 stars. No commits in the last 6 months.
Use this if you need to quickly and precisely edit the appearance or geometry of an existing 3D scene represented by a NeRF model using text prompts or physical shapes.
Not ideal if you need to create a 3D scene entirely from scratch without an existing NeRF, or if you prefer traditional 3D modeling software for editing.
Stars
129
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/cgtuebingen/SIGNeRF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rundiwu/DeepCAD
code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"
XingangPan/GAN2Shape
Code for GAN2Shape (ICLR2021 oral)
ayaanzhaque/instruct-nerf2nerf
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)
compphoto/Intrinsic
Repo for the papers "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023) and "Colorful...
mworchel/differentiable-shadow-mapping
Differentiable Shadow Mapping for Efficient Inverse Graphics (CVPR 2023)