Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People

TL;DR

This paper introduces a new dataset and a multi-view loss function to significantly improve the accuracy and completeness of single-image 3D human reconstruction, especially for clothed people.

Contribution

The paper presents a synthetic dataset of clothed humans and a novel multi-view loss for monocular shape estimation, enhancing reconstruction quality.

Findings

Outperforms previous state-of-the-art methods

Achieves higher accuracy and completeness in reconstructions

Demonstrates effective transfer from synthetic to real images

Abstract

We present a novel method to improve the accuracy of the 3D reconstruction of clothed human shape from a single image. Recent work has introduced volumetric, implicit and model-based shape learning frameworks for reconstruction of objects and people from one or more images. However, the accuracy and completeness for reconstruction of clothed people is limited due to the large variation in shape resulting from clothing, hair, body size, pose and camera viewpoint. This paper introduces two advances to overcome this limitation: firstly a new synthetic dataset of realistic clothed people, 3DVH; and secondly, a novel multiple-view loss function for training of monocular volumetric shape estimation, which is demonstrated to significantly improve generalisation and reconstruction accuracy. The 3DVH dataset of realistic clothed 3D human models rendered with diverse natural backgrounds is demonstrated to allows transfer to reconstruction from real images of people. Comprehensive comparative performance evaluation on both synthetic and real images of people demonstrates that the proposed method significantly outperforms the previous state-of-the-art learning-based single image 3D human shape estimation approaches achieving significant improvement of reconstruction accuracy, completeness, and quality. An ablation study shows that this is due to both the proposed multiple-view training and the new 3DVH dataset. The code and the dataset can be found at the project website: https://akincaliskan3d.github.io/MV3DH/.