PARE: Part Attention Regressor for 3D Human Body Estimation

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/}} read more

PDF Abstract ICCV 2021 PDF ICCV 2021 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
3D Human Pose Estimation 3DPW PARE PA-MPJPE 46.5 # 3
MPJPE 74.5 # 2
MPVPE 88.6 # 4
3D Multi-Person Pose Estimation AGORA PARE B-NMVE 167.7 # 2
B-NMJE 174.0 # 2
B-MVE 140.9 # 2
B-MPJPE 146.2 # 2
3D Human Pose Estimation AGORA PARE B-NMVE 167.7 # 2
B-NMJE 174.0 # 2
B-MVE 140.9 # 2
B-MPJPE 146.2 # 2

Methods


No methods listed for this paper. Add relevant methods here