gaussctrl

🎥 [ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing

Jing Wu*1 ,
Jia-Wang Bian*2 ,
Xinghui Li1,
Guangrun Wang1,
Ian Reid2,
Philip Torr1,
Victor Adrian Prisacariu1


* denotes equal contribution


1University of Oxford,

2Mohamed bin Zayed University of Artificial Intelligence

✨ News

• [3.18.2026] Nerfstudio, gsplat, LangSAM installations are updated and a docker environment is supported for easier repo reproduction.
• [9.4.2024] Our original results utilise stable-diffusion-v1-5 from runwayml for editing, which is now unavailable. Please change the diffusion checkpoint to other available models, e.g. CompVis/stable-diffusion-v1-4, by using --pipeline.diffusion_ckpt "CompVis/stable-diffusion-v1-4". Reproduce our original results by using the checkpoint --pipeline.diffusion_ckpt "jinggogogo/gaussctrl-sd15"

⚙️ Installation [Updated & Tested Mar 2026]

1️⃣ Conda Installation

• Tested on CUDA11.8 + Ubuntu22.04 + NeRFStudio1.0.0 (NVIDIA RTX A5000 24G)

Clone the repo.

git clone https://github.com/ActiveVisionLab/gaussctrl.git
cd gaussctrl

1. NeRFStudio and Lang-SAM

conda create -n gaussctrl python=3.8
conda activate gaussctrl
conda install cuda -c nvidia/label/cuda-11.8.0

Install dependencies for NerfStudio

# Install torch and tinycudann
pip install torch==2.1.2+cu118 torchvision==0.16.2+cu118 --extra-index-url https://download.pytorch.org/whl/cu118
pip install ninja git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch

# Install nerfstudio
pip install nerfstudio==1.0.0

# Update gsplat version for gc_model.py
pip install gsplat==0.1.3
pip install -r requirements.txt

pip install "huggingface_hub