12 papers
Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation
Zhonghua Yi, Hao Shi, Qi Jiang +3
Building pixel-level correspondence between event and image data is a fundamental task for multi-sensor systems. However, existing cross-modal matching methods are largely restrict…
E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes
Jiajun Zhai, Hao Shi, Shangwei Guo +2
Robotic Vision-Language-Action (VLA) models generalize well for open-ended manipulation, but their perception is fragile under sensing-stage degradations such as extreme low light,…
OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
Kai Luo, Hao Shi, Kunyu Peng +4
To address panoramic distortion, large search space, and identity ambiguity under a 360° FoV, OmniTrack++ adopts a feedback-driven framework that progressively refines perception…
Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions
Ze Dong, Hao Shi, Zejia Gao +3
Embodied robotic agents often perceive movies through an egocentric screen-view interface rather than native cinematic footage, introducing domain shifts such as viewpoint distorti…
OmniLens: Towards Universal Lens Aberration Correction via LensLib-to-Specific Domain Adaptation
Qi Jiang, Yao Gao, Shaohua Gao +7
Emerging universal Computational Aberration Correction (CAC) paradigms provide an inspiring solution to light-weight and high-quality imaging with a universal model trained on a le…
QuaDreamer: Controllable Panoramic Video Generation for Quadruped Robots
Sheng Wu, Fei Teng, Hao Shi +4
Panoramic cameras, capturing comprehensive 360-degree environmental data, are suitable for quadruped robots in surrounding perception and interaction with complex environments. How…