ayaanzhaque/instruct-nerf2nerf
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)
This project helps 3D content creators and researchers modify existing 3D scenes using simple text instructions. You input a pre-trained NeRF (Neural Radiance Field) model of a scene and a descriptive text prompt, and it outputs an edited NeRF reflecting your changes. This tool is ideal for 3D artists, game developers, or researchers who want to rapidly iterate on 3D environments without manual modeling.
850 stars. No commits in the last 6 months.
Use this if you need to quickly and intuitively alter the appearance or characteristics of a 3D scene represented by a NeRF model using natural language commands.
Not ideal if you're working with very high-resolution imagery (above 512 pixels on the longest side) or require extremely precise, pixel-level control for detailed 3D modeling.
Stars
850
Forks
79
Language
Python
License
MIT
Category
Last pushed
Feb 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ayaanzhaque/instruct-nerf2nerf"
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)
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)
cgtuebingen/SIGNeRF
SIGNeRF: Scene Integrated Generation for Neural Radiance Fields