PARE: Part Attention Regressor for 3D Human Body Estimation

TL;DR

PARE introduces a novel part attention mechanism for 3D human body estimation that improves robustness against occlusion by focusing on visible body parts and their neighbors, outperforming existing methods.

Contribution

The paper proposes the Part Attention Regressor (PARE), a new attention-based model that enhances 3D human body estimation accuracy under occlusion by using body-part-guided attention masks.

Findings

PARE achieves more accurate 3D reconstructions than previous methods.

PARE demonstrates robustness to partial occlusions in benchmarks.

Qualitative results show sensible attention masks learned by PARE.

Abstract

Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is observable. To address this, we introduce a soft attention mechanism, called the Part Attention REgressor (PARE), that learns to predict body-part-guided attention masks. We observe that state-of-the-art methods rely on global feature representations, making them sensitive to even small occlusions. In contrast, PARE's part-guided attention mechanism overcomes these issues by exploiting information about the visibility of individual body parts while leveraging information from neighboring body-parts to predict occluded parts. We show qualitatively that PARE learns sensible attention masks, and quantitative evaluation confirms that PARE achieves more accurate and robust reconstruction results than existing approaches on both occlusion-specific and standard benchmarks. The code and data are available for research purposes at {\small \url{https://pare.is.tue.mpg.de/}}