# Tex2Shape: Detailed Full Human Body Geometry From a Single Image

## TL;DR

Tex2Shape is a novel method that infers detailed full human body geometry, including face, hair, and clothing wrinkles, from a single image by transforming shape regression into an image-to-image translation task, achieving real-time performance.

## Contribution

The paper introduces a new approach that converts shape regression into an aligned image-to-image translation problem, enabling detailed 3D human body reconstruction from a single photo.

## Key findings

- Accurately infers detailed body shape including occluded parts.
- Generalizes well from synthetic training data to real images.
- Operates at interactive frame-rates for practical applications.

## Abstract

We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method.