2 papers
cs.CV2026
Revisiting the Current Frame: Physical-Trace-Guided Network Output Correction for Video Restoration
Yifeng Lin, Liuxiang Qiu, Guangming Ren +1
Video restoration methods exploit temporal information to recover information missing from degraded observations. However, reference frames within the sequence may introduce incons…
cs.CV2026
OmniVaT: Single Domain Generalization for Multimodal Visual-Tactile Learning
Liuxiang Qiu, Hui Da, Yuzhen Niu +3
Visual-tactile learning (VTL) enables embodied agents to perceive the physical world by integrating visual (VIS) and tactile (TAC) sensors. However, VTL still suffers from modality…