8 papers
QuacamFM: Quaternion-Constrained Flow Matching for Camera Pose Estimation
Bao-Long Tran, Cuong Le, Tahereh Dehdarirad +2
Camera pose estimation from multi-view images remains a challenge in computer vision. Traditional methods often address this problem using Structure-from-Motion (SfM) with bundle a…
CQF-HMR: Continuous Quaternion Flows for Probabilistic 3D Human Mesh Recovery from a Single Image
Cuong Le, Bao-Long Tran, Pavlo Melnyk +3
Recovering 3D digital humans from a single 2D image is an ill-posed computer vision problem due to the loss of depth information. Probabilistic 3D human pose estimation compensates…
Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection
Long Hoang Pham, Quoc Pham-Nam Ho, Huy-Hung Nguyen +10
Real-world deployment of traffic surveillance systems is bottlenecked by geographic domain shift, in which models trained in one city underperform when applied to an unseen target…
Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking
Duong Nguyen-Ngoc Tran, Ngoc Doan-Minh Huynh, Cu Quoc Le +10
Multi-camera 3D perception systems for warehouse scenes are trained largely on synthetic data and evaluated on physically captured environments. The resulting synthetic-to-real gap…
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…
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…
On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Lifting
Pavlo Melnyk, Cuong Le, Urs Waldmann +2
We consider monocular 3D human pose estimation (HPE), where the goal is to predict 3D human skeletal joints from a single 2D image, typically via 2D keypoint detection followed by…
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…