Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild
| Date | Stars |
|---|---|
| 2026-07-24 | 850 |
| 2026-07-25 | 850 |
| 2026-07-28 | 851 |
| 2026-07-30 | 851 |
| 2026-08-06 | 851 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<!-- # EMOCA -->
<h1 align="center">EMOCA: Emotion Driven Monocular Face Capture and Animation</h1>
<p align="center">
<p align="center">
<a href="https://ps.is.tuebingen.mpg.de/person/rdanecek"><strong>Radek Daněček</strong></a>
·
<a href="https://ps.is.tuebingen.mpg.de/person/black"><strong>Michael J. Black</strong></a>
·
<a href="https://sites.google.com/site/bolkartt"><strong>Timo Bolkart</strong></a>
</p>
<h2 align="center">CVPR 2022</h2>
<div align="center">
</div>
<!-- <a href="">
<img src="./assets/teaser.jpeg" alt="Logo" width="100%">
</a> -->
This repository is the official implementation of the [CVPR 2022](https://cvpr2022.thecvf.com/) paper [EMOCA: Emotion-Driven Monocular Face Capture and Animation](https://ps.is.mpg.de/uploads_file/attachment/attachment/686/EMOCA__CVPR22.pdf).
Please check out the [inferno](https://github.com/radekd91/inferno) library for a much superior face reconstruction network. You can find it in its [FaceReconstruction module](https://github.com/radekd91/inferno/tree/master/inferno_apps/FaceReconstruction).
<!--
<p align="center">
<img src="gdl_apps/EMOCA/EMOCA_gif_sparse_det.gif">
<img src="gdl_apps/EMOCA/EMOCA_gif_sparse_rec.gif">
</p>
-->
<p align="center">
<img src="gdl_apps/EMOCA/EMOCA_gif_sparse_det_rec.gif">
</p>
<p align="center">
<img src="gdl_apps/EMOCA/emoca.png">
</p>
<p align="center">Top row: input images. Middle row: coarse shape reconstruction. Bottom row: reconstruction with detailed displacements.<p align="center">
<p align="center">
<br>
<a href="https://pytorch.org/get-started/locally/"><img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-ee4c2c?logo=pytorch&logoColor=white"></a>
<a href="https://pytorchlightning.ai/"><img alt="Lightning" src="https://img.shields.io/badge/-Lightning-792ee5?logo=pytorchlightning&logoColor=white"></a>
<a href='https://emoca.is.tue.mpg.de/' style='padding-left: 0.5rem;'>
<img src='https://img.shields.io/badge/Project-Page-blue?style=flat&logo=Google%20chrome&logoColor=blue' alt='Project Page'></a>
<a href='https://youtu.be/zjMLB2-dVGw' style='padding-left: 0.5rem;'>
<img src='https://img.shields.io/badge/Youtube-Video-red?style=flat&logo=youtube&logoColor=red' alt='Youtube Video'>
</a>
<a href='https://ps.is.mpg.de/uploads_file/attachment/attachment/686/EMOCA__CVPR22.pdf'>
<img src='https://img.shields.io/badge/Paper-PDF-green?style=flat&logo=arXiv&logoColor=green' alt='Paper PDF'>
</a>
</p>
EMOCA takes a single in-the-wild image as input and reconstructs a 3D face with sufficient facial expression detail to convey the emotional state of the input image. EMOCA advances the state-of-the-art monocular face reconstruction in-the-wild, putting emphasis on accurate capture of emotional content. The official project page is [here](https://emoca.is.tue.mpg.de/index.html).
## !!! UPDATE !!!
**EMOCA is now deprecated.** For a better face reconstruction system, please head over to the [inferno libarary](https://github.com/radekd91/inferno/) and head over to [FaceReconstruction](https://github.com/radekd91/inferno/inferno_apps/FaceReconstruction) project.
## !!! UPDATE !!!
**EMOCA v2 is now out.** Complete the installation steps below and go to [EMOCA](gdl_apps/EMOCA) to test the demos.
Compared to the original model it produces:
1) Much better lip and eye alignment
2) Much better lip articulation
You can find the [comparison video here](https://download.is.tue.mpg.de/emoca/assets/emoca_v2_comparison.mp4)
This is achieved by:
1) Using a subset of mediapipe landmarks for mouth, eyes and eyebrows (as opposed to FAN landmarks that EMOCA v1 uses)
2) Using absolute landmark loss in combination with the relative losses (as opposed to only relative landmark losses in EMOCA v1)
3) Incorporating perceptual lip reading loss. Inspired by [spectre](https://filby89.github.io/spectre/). Big shout-out to these guys!
You will have to upgExcerpt of 11,230 characters
Read on GitHub
Radek Daněček · Max Planck Institute for Intelligent Systems
1.1k
Max Planck Institute for Intelligent Systems
12
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7d68fddceb268acf, topic:computer-vision, topic:3d-reconstruction, desc:3d reconstruction
matched fp:7d68fddceb268acf, topic:deep-learning, topic:pytorch