AI Rank
中文
← Open Source
mks0601

ExAvatar_RELEASE

Official PyTorch implementation of "Expressive Whole-Body 3D Gaussian Avatar", ECCV 2024.

Model DevelopmentArchitecturePython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
669
Stars
72
Forks
+0
This week
1
Contributors
Created 2024-09-12 · Updated 2026-10-14 · #15240 today
Top developers
mks0601

mks0601/ExAvatar_RELEASE is ranked 15,240 with 669 stars.

Same-category comparison

mks0601/ExAvatar_RELEASE is ranked 15,240 among these 8 peers; google-deepmind/hanabi-learning-environment is ranked 15,238.

Same-category comparison
NameRankMetrics
TropComplique/mtcnn-pytorch15,232
Language:
Jupyter Notebook
Stars:
669
Forks:
162
Description:
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks.
Waikato/moa15,233
Language:
Java
Stars:
669
Forks:
369
Description:
MOA is an open source framework for Big Data stream mining. It includes a collection of machine learning algorithms (classification, regression, clustering, outlier detection, concept drift detection and recommender systems) and tools for evaluation.
arunponnusamy/cvlib15,236
Language:
Python
Stars:
669
Forks:
126
Description:
A simple, high level, easy to use, open source Computer Vision library for Python.
google-deepmind/hanabi-learning-environment15,238
Language:
Python
Stars:
669
Forks:
164
Description:
hanabi_learning_environment is a research platform for Hanabi experiments.
sail-sg/lorahub15,242
Language:
Python
Stars:
669
Forks:
44
Description:
[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition.
PetarV-/DGI15,246
Language:
Python
Stars:
668
Forks:
135
Description:
Deep Graph Infomax (https://arxiv.org/abs/1809.10341).
cnkuangshi/LightCTR15,248
Language:
C++
Stars:
668
Forks:
138
Description:
Lightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate prediction based computational DAG, philosophy of Parameter Server and Ring-AllReduce collective communication.
zhangxiaosong18/FreeAnchor15,253
Language:
Python
Stars:
668
Forks:
108
Description:
FreeAnchor: Learning to Match Anchors for Visual Object Detection (NeurIPS 2019).
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModel Development
SubcategoryArchitecture
Keywords3D, Computer vision
Stars669
Forks72
Contributors1
Created date2024-09-12
Updated date2026-10-14
Stars in 1 day0
Stars in 7 days0
Rank15,240
Previous rank15,063
Rank change-177
7-day stars rank14,885
Previous 7-day stars rank14,900
7-day stars rank change15
Total stars rank15,413
Previous total stars rank15,391
Total stars rank change-22
README summary

Expressive Whole-Body 3D Gaussian Avatar (ECCV 2024) Project Page | Paper | Video This is an reimplmentation of **Expressive Whole-Body 3D Gaussian Avatar (ECCV 2024)** by the first author after leaving Meta. All the code use public assets without any Meta's internal-only modules. All the results in the camera-ready version and demo videos in the website are from this reimplmented code. ExAvatar is designed as a combination of 1) whole-body (body, hands, and face) drivability of SMPL

-X and 2) strong appearance modeling capability of 3DGS. Yes, it's me, Gyeongsik in the video :), taken in front of my apartment with my mobile phone. For more high-resolution demo videos, please visit our website . Install Creating and animating avatars from a phone scan 1. To create an avatar, you first need to fit SMPL-X to a video with a single person. Then, go to here to create and animate the avatar. Creating and animating avatars from X

-Humans dataset Go to here Reference

Frequently asked questions

How many stars and forks are recorded?

mks0601/ExAvatar_RELEASE has 669 stars and 72 forks.

What is the repository rank?

mks0601/ExAvatar_RELEASE is ranked 15,240.

What language and category are recorded?

mks0601/ExAvatar_RELEASE has 669 stars, uses Python and belongs to Model Development.

Which repository is closest in rank?

mks0601/ExAvatar_RELEASE is compared with google-deepmind/hanabi-learning-environment, ranked 15,238 with 669 stars.

README

Expressive Whole-Body 3D Gaussian Avatar (ECCV 2024)

Project Page | Paper | Video

  • This is an reimplmentation of Expressive Whole-Body 3D Gaussian Avatar (ECCV 2024) by the first author after leaving Meta. All the code use public assets without any Meta's internal-only modules. All the results in the camera-ready version and demo videos in the website are from this reimplmented code.
  • ExAvatar is designed as a combination of 1) whole-body (body, hands, and face) drivability of SMPL-X and 2) strong appearance modeling capability of 3DGS.

Yes, it's me, Gyeongsik in the video :), taken in front of my apartment with my mobile phone. For more high-resolution demo videos, please visit our website.

Install

conda env create -f environment.yml
conda activate exavatar

Creating and animating avatars from a phone scan

  1. To create an avatar, you first need to fit SMPL-X to a video with a single person. Go to here.
  2. Then, go to here to create and animate the avatar.

Creating and animating avatars from X-Humans dataset

Reference

@inproceedings{moon2024exavatar,
  title={Expressive Whole-Body 3D Gaussian Avatar},
  author = {Moon, Gyeongsik and Shiratori, Takaaki and Saito, Shunsuke},  
  booktitle={ECCV},
  year={2024}
}
Nearby in the ranking
Similar items