CASIA OpenIR  > 多模态人工智能系统全国重点实验室
Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images
Yu C(于畅)1,2; Zhu XY(朱翔昱)1,2; Zhang XM(张小梅)1,2; Zhang ZX(张兆翔)1,2,3; Lei Z(雷震)1,2,3
2023
Conference NameIEEE Conference on Computer Vision and Pattern Recognition
Conference Date2023年6月
Conference Place加拿大
Abstract

The function of constructing the hierarchy of objects is important to the visual process of the human brain. Previous studies have successfully adopted capsule networks to decompose the digits and faces into parts in an unsupervised manner to investigate the similar perception mechanism of neural networks. However, their descriptions are restricted to the 2D space, limiting their capacities to imitate the intrinsic 3D perception ability of humans. In this paper, we propose an Inverse Graphics Capsule Network (IGC-Net) to learn the hierarchical 3D face representations from large-scale unlabeled images. The core of IGC-Net is a new type of capsule, named graphics capsule, which represents 3D primitives with interpretable parameters in computer graphics (CG), including depth, albedo, and 3D pose. Specifically, IGC-Net first decomposes the objects into a set of semantic-consistent part-level descriptions and then assembles them into object-level descriptions to build the hierarchy. The learned graphics capsules reveal how the neural networks, oriented at visual perception, understand faces as a hierarchy of 3D models. Besides, the discovered parts can be deployed to the unsupervised face segmentation task to evaluate the semantic consistency of our method. Moreover, the part-level descriptions with explicit physical meanings provide insight into the face analysis that originally runs in a black box, such as the importance of shape and texture for face recognition. Experiments on CelebA, BP4D, and Multi-PIE demonstrate the characteristics of our IGC-Net.

Sub direction classification生物特征识别
planning direction of the national heavy laboratory可解释人工智能
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/56727
Collection多模态人工智能系统全国重点实验室
Corresponding AuthorZhu XY(朱翔昱)
Affiliation1.中国科学院自动化所
2.中国科学院大学
3.Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yu C,Zhu XY,Zhang XM,et al. Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images[C],2023.
Files in This Item: Download All
File Name/Size DocType Version Access License
Yu_Graphics_Capsule_(2173KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yu C(于畅)]'s Articles
[Zhu XY(朱翔昱)]'s Articles
[Zhang XM(张小梅)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yu C(于畅)]'s Articles
[Zhu XY(朱翔昱)]'s Articles
[Zhang XM(张小梅)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yu C(于畅)]'s Articles
[Zhu XY(朱翔昱)]'s Articles
[Zhang XM(张小梅)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Yu_Graphics_Capsule_Learning_Hierarchical_3D_Face_Representations_From_2D_Images_CVPR_2023_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.