PARE: Part Attention Regressor for 3D Human Body Estimation

By Muhammed Kocabas, Chun-Hao Paul Huang, Otmar Hilliges, Michael J. Black. IEEE International Conference on Computer Vision, 2021

524 citations recorded by the source corpus.

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 https://pare.is.tue.mpg.de/

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Endocrinology, Diabetes and Metabolism

View Paper: https://www.semanticscholar.org/paper/35e8508edf2e754af17503eea2d151c7504b7314

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Endocrinology, Diabetes and Metabolism

Citations in the corpus

ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation (2022, methodology): “We use axis-angle for rotation and use the weak perspective camera model to estimate the translations [5,30,35,54,83].”
ICON: Implicit Clothed humans Obtained from Normals (2021, methodology): “ICON takes as input an RGB image of a segmented clothed human and a SMPL body estimated from the image [32].”
Humans in 4D: Reconstructing and Tracking Humans with Transformers (2023, methodology): “For a direct comparison of the effect of the backbone, Model B1 implements HMR with a ResNet-50 backbone and an MLP-based head implementing IEF (Iterative Error Feedback [9, 30]).”
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation (2022, unknown): “Even though accurate articulated poses can also be obtained by PARE, we can see clear pixel-misalignment of its results overlaid on the images, suffering from its inferior global rotation estimation.”
HuMoR: 3D Human Motion Model for Robust Pose Estimation (2021, background): “Other works have addressed occlusions but only on static images [7, 90, 64, 22, 38].”