hrz2000/CustomNeRF
[CVPR 2024] Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training
This project helps 3D artists and content creators modify specific objects within a 3D scene that was created from photos (a NeRF model). You provide an existing NeRF model and either a text description or a reference image. The output is a new 3D scene where the specified object has been visually transformed according to your input, while keeping the background unchanged.
No commits in the last 6 months.
Use this if you need to precisely edit foreground elements in a 3D NeRF scene using text prompts or a reference image, ensuring the background remains intact and the edits are consistent from multiple viewpoints.
Not ideal if you need to create entire 3D scenes from scratch or perform broad, non-localized edits across the whole scene.
Stars
44
Forks
1
Language
Python
License
—
Category
Last pushed
Apr 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hrz2000/CustomNeRF"
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)