BBoxMaskPose v2: Expanding Mutual Conditioning to 3D
This work addresses the problem of accurate human pose estimation in crowded scenes for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles crowded 2D human pose estimation by introducing PMPose and BMPv2, which improve performance on crowded scenes without harming standard scenes, achieving state-of-the-art gains of 1.5 AP on COCO and 6 AP on OCHuman, and showing that these 2D advances benefit 3D pose estimation in crowded settings.
Most 2D human pose estimation benchmarks are nearly saturated, with the exception of crowded scenes. We introduce PMPose, a top-down 2D pose estimator that incorporates the probabilistic formulation and the mask-conditioning. PMPose improves crowded pose estimation without sacrificing performance on standard scenes. Building on this, we present BBoxMaskPose v2 (BMPv2) integrating PMPose and an enhanced SAM-based mask refinement module. BMPv2 surpasses state-of-the-art by 1.5 average precision (AP) points on COCO and 6 AP points on OCHuman, becoming the first method to exceed 50 AP on OCHuman. We demonstrate that BMP's 2D prompting of 3D model improves 3D pose estimation in crowded scenes and that advances in 2D pose quality directly benefit 3D estimation. Results on the new OCHuman-Pose dataset show that multi-person performance is more affected by pose prediction accuracy than by detection. The code, models, and data are available on https://MiraPurkrabek.github.io/BBox-Mask-Pose/.