PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

TL;DR

This paper introduces PIFuHD, a multi-level neural network architecture that enables high-resolution 3D human shape reconstruction from single images, overcoming hardware memory limitations to produce detailed results.

Contribution

The authors propose a novel multi-level, end-to-end trainable framework that combines coarse global reasoning with fine detailed estimation for 3D human digitization.

Findings

Outperforms existing methods on high-resolution 3D human reconstruction

Effectively leverages 1k-resolution input images for detailed outputs

Demonstrates significant improvement in reconstruction detail and accuracy

Abstract

Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks. Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images. We argue that this limitation stems primarily form two conflicting requirements; accurate predictions require large context, but precise predictions require high resolution. Due to memory limitations in current hardware, previous approaches tend to take low resolution images as input to cover large spatial context, and produce less precise (or low resolution) 3D estimates as a result. We address this limitation by formulating a multi-level architecture that is end-to-end trainable. A coarse level observes the whole image at lower resolution and focuses on holistic reasoning. This provides context to an fine level which estimates highly detailed geometry by observing higher-resolution images. We demonstrate that our approach significantly outperforms existing state-of-the-art techniques on single image human shape reconstruction by fully leveraging 1k-resolution input images.