Shunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima, Angjoo Kanazawa, Hao Li

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

pp.2304-2314, arXiv:1905.05172

International Conference on Computer Vision 2019

http://iccv2019.thecvf.com/, https://github.com/shunsukesaito/PIFu

We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object Download The Great Sejong. 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 sierra 다운로드. 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 can produce high-resolution surfaces including largely unseen regions such as the back of a person 타요 차고지 놀이. 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 wget windows. Furthermore, while previous techniques are designed to process either a single image or multiple views, PIFu extends naturally to arbitrary number of views 극비수사 다운로드. We demonstrate high-resolution and robust reconstructions on real world images from the DeepFashion dataset, which contains a variety of challenging clothing types Windows 7 Chrome. 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 Download pc katok photo.