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

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

CoRR abs/1905.05172 (2019)

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 '90s Song. 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 Download Tomb Raider. 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 Mode Converter 다운로드. 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 Download Rio 2 dubbed. Furthermore, while previous techniques are designed to process either a single image or multiple views, PIFu extends naturally to arbitrary number of views Download this path. We demonstrate high-resolution and robust reconstructions on real world images from the DeepFashion dataset, which contains a variety of challenging clothing types 윈도우10 제품키. 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 심즈 3.