FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second

TL;DR

FACSIMILE (FAX) is a fast, accurate method for detailed 3D body shape estimation from a single image, operating in under a second without depth supervision, and is easy to implement and deploy.

Contribution

The paper introduces FACSIMILE, a novel image-translation network that estimates detailed 3D body geometry from a single photo efficiently and without depth supervision.

Findings

Achieves detailed body shape estimation in less than a second.

Outperforms state-of-the-art methods in accuracy.

Operates without requiring depth data during training.

Abstract

Current methods for body shape estimation either lack detail or require many images. They are usually architecturally complex and computationally expensive. We propose FACSIMILE (FAX), a method that estimates a detailed body from a single photo, lowering the bar for creating virtual representations of humans. Our approach is easy to implement and fast to execute, making it easily deployable. FAX uses an image-translation network which recovers geometry at the original resolution of the image. Counterintuitively, the main loss which drives FAX is on per-pixel surface normals instead of per-pixel depth, making it possible to estimate detailed body geometry without any depth supervision. We evaluate our approach both qualitatively and quantitatively, and compare with a state-of-the-art method.