activity
20242026
collaborators

8 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…