7 papers · 1 filter
Noise-Robust Tiny Object Localization with Flows
Huixin Sun, Linlin Yang, Ronyu Chen +4
Despite significant advances in generic object detection, a persistent performance gap remains for tiny objects compared to normal-scale objects. We demonstrate that tiny objects a…
Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses
Qiuxia Lin, Kerui Gu, Linlin Yang +1
Online test-time adaptation for 3D human pose estimation is used for video streams that differ from training data. Ground truth 2D poses are used for adaptation, but only estimated…
Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
Qiuxia Lin, Rongyu Chen, Kerui Gu +1
This work highlights a semantics misalignment in 3D human pose estimation. For the task of test-time adaptation, the misalignment manifests as overly smoothed and unguided predicti…
Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery
Fengyuan Yang, Kerui Gu, Ha Linh Nguyen +2
Accurate camera motion estimation is essential for recovering global human motion in world coordinates from RGB video inputs. SLAM is widely used for estimating camera trajectory a…
KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation
Fengyuan Yang, Kerui Gu, Angela Yao
2D keypoints are commonly used as an additional cue to refine estimated 3D human meshes. Current methods optimize the pose and shape parameters with a reprojection loss on the prov…
Learning Unorthogonalized Matrices for Rotation Estimation
Kerui Gu, Zhihao Li, Shiyong Liu +6
Estimating 3D rotations is a common procedure for 3D computer vision. The accuracy depends heavily on the rotation representation. One form of representation -- rotation matrices -…