8 papers
S23DR 2026 Winning Solution
Jan Skvrna, Miroslav Purkrabek, Lukas Neumann
This text presents the winning solution to the S23DR 2026 challenge for structured 3D wireframe reconstruction from sparse SfM, fitted depth, and semantic segmentations. The method…
BBoxMaskPose v2: Expanding Mutual Conditioning to 3D
Miroslav Purkrabek, Constantin Kolomiiets, Jiri Matas
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 probabi…
SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds
Constantin Kolomiiets, Miroslav Purkrabek, Jiri Matas
Segment Anything (SAM) provides an unprecedented foundation for human segmentation, but may struggle under occlusion, where keypoints may be partially or fully invisible. We adapt…
BLANKET: Anonymizing Faces in Infant Video Recordings
Ditmar Hadera, Jan Cech, Miroslav Purkrabek +1
Ensuring the ethical use of video data involving human subjects, particularly infants, requires robust anonymization methods. We propose BLANKET (Baby-face Landmark-preserving ANon…
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
Miroslav Purkrabek, Jiri Matas
Human pose estimation methods work well on isolated people but struggle with multiple-bodies-in-proximity scenarios. Previous work has addressed this problem by conditioning pose e…
Human Pose-Constrained UV Map Estimation
Matej Suchanek, Miroslav Purkrabek, Jiri Matas
UV map estimation is used in computer vision for detailed analysis of human posture or activity. Previous methods assign pixels to body model vertices by comparing pixel descriptor…