PARE: Part Attention Regressor for 3D Human Body Estimation
This addresses the issue of occlusion sensitivity in 3D human body estimation for applications like computer vision and robotics, representing an incremental improvement over prior methods.
The paper tackles the problem of 3D human pose and shape estimation being sensitive to partial occlusion by introducing PARE, a part attention regressor that uses soft attention masks to improve robustness, achieving more accurate and robust reconstruction results than existing methods on occlusion-specific and standard benchmarks.
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/}}