Label-Free Target-Domain Adaptation for Unconstrained Event-Image Feature Matching via Dual-Stage Distillation
arXiv:2607.10082v1 Announce Type: new Abstract: 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 restricted by their reliance on either matching labels or strictly aligned hardware, which limits them to unlabeled and unconstrained real-world scenarios where neither matching ground truth nor prior sensor relationships are available. To address this, we propose a novel two-sta...
arXiv cs.CV
·Zhonghua Yi, Hao Shi, Qi Jiang, Yufan Zhang, Kailun Yang, Kaiwei Wang
·
// relacionados
Leia também
Editorial
Uma memória para o que os óculos veem: o problema difícil de lembrar a vida inteira
Blog
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
Blog
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
Blog