FuRPE: Learning Full-body Reconstruction from Part Experts

TL;DR

FuRPE introduces a novel framework for full-body reconstruction that leverages part-experts, pseudo labels, and innovative training strategies to improve accuracy and robustness, significantly outperforming existing methods.

Contribution

The paper presents FuRPE, a new approach using pseudo labels and expert features to enhance full-body reconstruction from limited annotated data.

Findings

Substantial performance improvements over existing methods

Effective pseudo label generation with expert guidance

Robust training strategy reduces bias and improves accuracy

Abstract

In the field of full-body reconstruction, the scarcity of annotated data often impedes the efficacy of prevailing methods. To address this issue, we introduce FuRPE, a novel framework that employs part-experts and an ingenious pseudo ground-truth selection scheme to derive high-quality pseudo labels. These labels, central to our approach, equip our network with the capability to efficiently learn from the available data. Integral to FuRPE is a unique exponential moving average training strategy and expert-derived feature distillation strategy. These novel elements of FuRPE not only serve to further refine the model but also to reduce potential biases that may arise from inaccuracies in pseudo labels, thereby optimizing the network's training process and enhancing the robustness of the model. We apply FuRPE to train both two-stage and fully convolutional single-stage full-body reconstruction networks. Our exhaustive experiments on numerous benchmark datasets illustrate a substantial performance boost over existing methods, underscoring FuRPE's potential to reshape the state-of-the-art in full-body reconstruction.