From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Weiguang, Yang, Chaolong, Ye, Jianan, Zhang, Rui, Yan, Yuyao, Yang, Xi, Dong, Bin, Hussain, Amir, Huang, Kaizhu
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916540529508352
author Zhao, Weiguang
Yang, Chaolong
Ye, Jianan
Zhang, Rui
Yan, Yuyao
Yang, Xi
Dong, Bin
Hussain, Amir
Huang, Kaizhu
author_facet Zhao, Weiguang
Yang, Chaolong
Ye, Jianan
Zhang, Rui
Yan, Yuyao
Yang, Xi
Dong, Bin
Hussain, Amir
Huang, Kaizhu
contents While weakly supervised multi-view face reconstruction (MVR) is garnering increased attention, one critical issue still remains open: how to effectively interact and fuse multiple image information to reconstruct high-precision 3D models. In this regard, we propose a novel pipeline called Deep Fusion MVR (DF-MVR) to explore the feature correspondences between multi-view images and reconstruct high-precision 3D faces. Specifically, we present a novel multi-view feature fusion backbone that utilizes face masks to align features from multiple encoders and integrates one multi-layer attention mechanism to enhance feature interaction and fusion, resulting in one unified facial representation. Additionally, we develop one concise face mask mechanism that facilitates multi-view feature fusion and facial reconstruction by identifying common areas and guiding the network's focus on critical facial features (e.g., eyes, brows, nose, and mouth). Experiments on Pixel-Face and Bosphorus datasets indicate the superiority of our model. Without 3D annotation, DF-MVR achieves 5.2% and 3.0% RMSE improvement over the existing weakly supervised MVRs respectively on Pixel-Face and Bosphorus dataset. Code will be available publicly at https://github.com/weiguangzhao/DF_MVR.
format Preprint
id arxiv_https___arxiv_org_abs_2204_03842
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion
Zhao, Weiguang
Yang, Chaolong
Ye, Jianan
Zhang, Rui
Yan, Yuyao
Yang, Xi
Dong, Bin
Hussain, Amir
Huang, Kaizhu
Computer Vision and Pattern Recognition
While weakly supervised multi-view face reconstruction (MVR) is garnering increased attention, one critical issue still remains open: how to effectively interact and fuse multiple image information to reconstruct high-precision 3D models. In this regard, we propose a novel pipeline called Deep Fusion MVR (DF-MVR) to explore the feature correspondences between multi-view images and reconstruct high-precision 3D faces. Specifically, we present a novel multi-view feature fusion backbone that utilizes face masks to align features from multiple encoders and integrates one multi-layer attention mechanism to enhance feature interaction and fusion, resulting in one unified facial representation. Additionally, we develop one concise face mask mechanism that facilitates multi-view feature fusion and facial reconstruction by identifying common areas and guiding the network's focus on critical facial features (e.g., eyes, brows, nose, and mouth). Experiments on Pixel-Face and Bosphorus datasets indicate the superiority of our model. Without 3D annotation, DF-MVR achieves 5.2% and 3.0% RMSE improvement over the existing weakly supervised MVRs respectively on Pixel-Face and Bosphorus dataset. Code will be available publicly at https://github.com/weiguangzhao/DF_MVR.
title From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2204.03842