Super-resolution 3D Human Shape from a Single Low-Resolution Image

TL;DR

This paper introduces a new end-to-end framework that reconstructs high-detail 3D human shapes from single low-resolution images without auxiliary data, outperforming previous methods in detail accuracy.

Contribution

The novel framework uses an implicit function and a unique loss to learn super-resolution 3D human shape reconstruction from low-res images.

Findings

Achieves high-detail surface reconstruction from low-resolution images.

Outperforms previous methods in detail accuracy.

Effective without auxiliary data.

Abstract

We propose a novel framework to reconstruct super-resolution human shape from a single low-resolution input image. The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as surface normal or a parametric model to reconstruct high-detail shape. The proposed framework represents the reconstructed shape with a high-detail implicit function. Analogous to the objective of 2D image super-resolution, the approach learns the mapping from a low-resolution shape to its high-resolution counterpart and it is applied to reconstruct 3D shape detail from low-resolution images. The approach is trained end-to-end employing a novel loss function which estimates the information lost between a low and high-resolution representation of the same 3D surface shape. Evaluation for single image reconstruction of clothed people demonstrates that our method achieves high-detail surface reconstruction from low-resolution images without auxiliary data. Extensive experiments show that the proposed approach can estimate super-resolution human geometries with a significantly higher level of detail than that obtained with previous approaches when applied to low-resolution images.