2019年
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
- ,
- ,
- ,
- ,
- ,
- 巻
- 2019-October
- 号
- 開始ページ
- 2304
- 終了ページ
- 2314
- 記述言語
- 英語
- 掲載種別
- DOI
- 10.1109/ICCV.2019.00239
- 出版者・発行元
- IEEE COMPUTER SOC
We introduce Pixel-aligned Implicit Function (PIFu), an implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object. Using PIFu, we propose an end-to-end deep learning method for digitizing highly detailed clothed humans that can infer both 3D surface and texture from a single image, and optionally, multiple input images. Highly intricate shapes, such as hairstyles, clothing, as well as their variations and deformations can be digitized in a unified way. Compared to existing representations used for 3D deep learning, PIFu produces high-resolution surfaces including largely unseen regions such as the back of a person. In particular, it is memory efficient unlike the voxel representation, can handle arbitrary topology, and the resulting surface is spatially aligned with the input image. Furthermore, while previous techniques are designed to process either a single image or multiple views, PIFu extends naturally to arbitrary number of views. We demonstrate high-resolution and robust reconstructions on real world images from the DeepFashion dataset, which contains a variety of challenging clothing types. Our method achieves state-of-the-art performance on a public benchmark and outperforms the prior work for clothed human digitization from a single image.
- リンク情報
-
- DOI
- https://doi.org/10.1109/ICCV.2019.00239
- arXiv
- http://arxiv.org/abs/arXiv:1905.05172
- Web of Science
- https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000531438102044&DestApp=WOS_CPL
- Scopus
- https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85081892126&origin=inward
- Scopus Citedby
- https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85081892126&origin=inward
- URL
- http://arxiv.org/abs/1905.05172v3
- URL
- http://arxiv.org/pdf/1905.05172v3 本文へのリンクあり
- ID情報
-
- DOI : 10.1109/ICCV.2019.00239
- ISSN : 1550-5499
- arXiv ID : arXiv:1905.05172
- SCOPUS ID : 85081892126
- Web of Science ID : WOS:000531438102044