2 papers
cs.CV2026
Unconstrained Multi-view Human Pose Estimation with Algebraic Priors
Xiaolin Qin, Qianlei Wang, Jiacen Liu +3
Recovering 3D human pose from multi-view imagery typically relies on precise camera calibration, which is often unavailable in real-world scenarios, thereby severely limiting the a…
cs.CV2024
Fourier Boundary Features Network with Wider Catchers for Glass Segmentation
Xiaolin Qin, Jiacen Liu, Qianlei Wang +3
Glass largely blurs the boundary between the real world and the reflection. The special transmittance and reflectance quality have confused the semantic tasks related to machine vi…