MExECON: Multi-view Extended Explicit Clothed humans Optimized via Normal integration

TL;DR

MExECON is a multi-view pipeline for 3D clothed human reconstruction that enhances geometry and detail accuracy by jointly optimizing body models across views and integrating normal maps, without retraining networks.

Contribution

It introduces the JMBO algorithm for joint multi-view body optimization and extends single-view ECON to multi-view, improving 3D reconstruction quality without additional network training.

Findings

Improves 3D reconstruction fidelity over single-view methods.

Achieves detailed surface capture like clothing folds and hairstyles.

Performs competitively with modern few-shot reconstruction methods.

Abstract

This work presents MExECON, a novel pipeline for 3D reconstruction of clothed human avatars from sparse multi-view RGB images. Building on the single-view method ECON, MExECON extends its capabilities to leverage multiple viewpoints, improving geometry and body pose estimation. At the core of the pipeline is the proposed Joint Multi-view Body Optimization (JMBO) algorithm, which fits a single SMPL-X body model jointly across all input views, enforcing multi-view consistency. The optimized body model serves as a low-frequency prior that guides the subsequent surface reconstruction, where geometric details are added via normal map integration. MExECON integrates normal maps from both front and back views to accurately capture fine-grained surface details such as clothing folds and hairstyles. All multi-view gains are achieved without requiring any network re-training. Experimental results show that MExECON consistently improves fidelity over the single-view baseline and achieves competitive performance compared to modern few-shot 3D reconstruction methods.