· 2019
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
- 1,233citations
- 2019year
Short summary
PIFu, a new implicit representation, digitizes highly detailed clothed humans from single or multiple 2D images, inferring 3D surface and texture, even for unseen regions like the back.
AI-generated from the title and abstract; the full text is not read.
Key points
- PIFu aligns 2D pixels with 3D context for detailed human digitization.
- It infers 3D surface and texture from single or multiple images.
- The method reconstructs intricate details like hairstyles and clothing, including unseen areas.
- PIFu is memory-efficient and handles arbitrary topology, unlike voxel methods.
- It achieves state-of-the-art results on the DeepFashion dataset for clothed human digitization.
AI-generated from the title and abstract; the full text is not read.
Abstract
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.
The authors' abstract, as published at the source., 2019 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computational Mechanics
Computational MechanicsEngineering