choyingw/Cross-Modal-Perceptionist
CVPR 2022: Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?
This project explores the intriguing connection between a person's voice and the unique geometry of their face. It takes an audio recording of a person speaking and predicts a 3D model of their face, including details about its shape and structure. This could be used by researchers in fields like forensics, biometrics, or computational psychology to analyze underlying physiological correlations.
131 stars. No commits in the last 6 months.
Use this if you are a researcher studying the complex relationships between vocal characteristics and facial biometrics, particularly for understanding genetic or physiological links.
Not ideal if you need to identify individuals from their voice, as this project focuses on predicting general facial geometry rather than specific person identification.
Stars
131
Forks
15
Language
Python
License
MIT
Category
Last pushed
Dec 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/choyingw/Cross-Modal-Perceptionist"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrikhuber/eos
A lightweight 3D Morphable Face Model library in modern C++
Uason-Chen/CTR-GCN
[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for...
PeterL1n/BackgroundMattingV2
Real-Time High-Resolution Background Matting
PeterL1n/RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Zielon/MICA
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]