面向事件-帧非对称立体的双向跨模态提示
Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
把事件与帧两种模态各自投影到对方域、在目标规范空间做细粒度对齐的双向提示思路，可直接迁移到其他跨模态立体匹配或跨传感器融合的稠密对应任务中，缓解模态鸿沟导致的域特有线索被边缘化问题。
原文依据 a novel bidirectional cross-modal prompting framework that fully exploits semantic and structural features from both domains for robust matching
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论传统基于帧的相机能够捕获丰富的上下文信息，但在动态场景中受限于时序分辨率且存在运动模糊。事件相机提供了一种替代性的视觉表示，具有更高的动态范围且不受上述限制。两种模态的互补特性使得事件-帧非对称立体在快速运动和具有挑战性的光照条件下有望实现可靠的三维感知。然而，模态鸿沟往往导致对跨模态立体匹配至关重要的域特有线索被边缘化。本文提出 Bi-CMPStereo，一种新颖的双向跨模态提示框架，充分利用两个域的语义与结构特征以实现鲁棒匹配。该方法在目标规范空间内学习精细对齐的立体表示，并通过将每种模态分别投影到事件域与帧域来整合互补表示。大量实验表明，该方法在精度与泛化性上显著优于最优方法。
英文原文摘要 1079 字符
Conventional frame-based cameras capture rich contextual information but suffer from limited temporal resolution and motion blur in dynamic scenes. Event cameras offer an alternative visual representation with higher dynamic range free from such limitations. The complementary characteristics of the two modalities make event-frame asymmetric stereo promising for reliable 3D perception under fast motion and challenging illumination. However, the modality gap often leads to marginalization of domain-specific cues essential for cross-modal stereo matching. In this paper, we introduce Bi-CMPStereo, a novel bidirectional cross-modal prompting framework that fully exploits semantic and structural features from both domains for robust matching. Our approach learns finely aligned stereo representations within a target canonical space and integrates complementary representations by projecting each modality into both event and frame domains. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods in accuracy and generalization.