Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up

Code for PhysDreamer

NotificationsYou must be signed in to change notification settings

Ramtinhoss/PhysDreamer

 
 

Repository files navigation

teaser-figure

Useage

Setup enviroment

Install diff-gaussian-rasterization at:https://github.com/graphdeco-inria/diff-gaussian-rasterization

conda create -n physdreamer pythonconda activate physdreamerpip install -r requirements.txtpython setup.py install

Download the scenes and optimized models from Hugging Face

Download the scenes and optimized velocity and material fields from:https://huggingface.co/datasets/YunjinZhang/PhysDreamer/tree/main

Put folders of these scenes todata/physics_dreamer/xxx, e.g.data/physics_dreamer/carnations

Put pretrained models to./models.

Seedataset_dir andmodel_list ininference/configs/carnation.py to match the path of dataset and pretrained models.

Run inference

cd projects/inferencebash run.sh

Acknowledgement

This codebase used lots of source code from:

  1. https://github.com/graphdeco-inria/gaussian-splatting
  2. https://github.com/zeshunzong/warp-mpm
  3. https://github.com/PingchuanMa/NCLaw

We thank the authors of these projects.

Citations

@article{zhang2024physdreamer,    title={{PhysDreamer}: Physics-Based Interaction with 3D Objects via Video Generation},    author={Tianyuan Zhang and Hong-Xing Yu and Rundi Wu and            Brandon Y. Feng and Changxi Zheng and Noah Snavely and Jiajun Wu and William T. Freeman},    journal={arxiv},    year={2024}}

About

Code for PhysDreamer

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python99.9%
  • Shell0.1%

[8]ページ先頭

©2009-2025 Movatter.jp