5 papers
On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Lifting
Pavlo Melnyk, Cuong Le, Urs Waldmann +2
Estimating 3D from 2D is one of the central tasks in computer vision. In this work, we consider the monocular setting, i.e. single-view input, for 3D human pose estimation (HPE), w…
Benchmark Dataset for Catalysis on 2D MXenes
Pavlo Melnyk, Anmar Karmush, Mårten Wadenbäck +4
Merging first-principles calculations with machine learning (ML), we aim to accelerate the exploration of catalytic behaviour in novel materials. We focus on two-dimensional (2D) T…
Flow Matching for Probabilistic Monocular 3D Human Pose Estimation
Cuong Le, Pavlo Melnyk, Bastian Wandt +1
Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain inco…
QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
Cuong Le, Pavlo Melnyk, Urs Waldmann +2
Vision-based 3D human motion capture from videos remains a challenge in computer vision. Traditional 3D pose estimation approaches often ignore the temporal consistency between fra…
O Learning Deep O()-Equivariant Hyperspheres
Pavlo Melnyk, Michael Felsberg, Mårten Wadenbäck +2
In this paper, we utilize hyperspheres and regular -simplexes and propose an approach to learning deep features equivariant under the transformations of D reflections and rot…