x^2-Fusion：事件边缘空间中的跨模态与跨维度流估计
x^2-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space
把事件相机输出的时空边缘当作统一的潜空间锚点，让图像与激光雷达特征显式对齐到同一表示，再做可靠性感知的自适应融合；这套「以事件边缘场为共享潜空间」的思路可直接迁移到其他多传感器融合任务（如深度补全、BEV 感知），跨维度对比学习也可用于耦合 2D 与 3D 运动估计。
原文依据 Event cameras naturally provide a spatiotemporal edge signal, which we can treat as an intrinsic edge field to anchor a unified latent representation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论估计稠密二维光流与三维场景流对动态场景理解至关重要。近期工作结合图像、激光雷达与事件数据联合预测二维与三维运动，但多数方法在彼此分离的异构特征空间中运作。由于缺乏一个所有模态都能对齐的共享潜空间，这些系统依赖多个模态专属模块，导致跨传感器失配无法解决，融合也变得不必要地复杂。事件相机天然提供时空边缘信号，我们可将其视为一种内在边缘场，用以锚定统一的潜变量表示，称为事件边缘空间。基于这一思想，我们提出 x^2-Fusion，将多模态融合重新表述为表示统一：由事件导出的时空边缘定义一个以边缘为中心的齐性空间，图像与激光雷达特征在该共享表示中被显式对齐。在该空间内，我们执行可靠性感知的自适应融合，以估计模态可靠性并在退化条件下强调稳定线索。我们进一步采用跨维度对比学习，将二维光流与三维场景流紧密耦合。在合成与真实基准上的大量实验表明，x^2-Fusion 在标准条件下达到最优精度，并在挑战性场景中带来显著提升。
英文原文摘要 1365 字符
Estimating dense 2D optical flow and 3D scene flow is essential for dynamic scene understanding. Recent work combines images, LiDAR, and event data to jointly predict 2D and 3D motion, yet most approaches operate in separate heterogeneous feature spaces. Without a shared latent space that all modalities can align to, these systems rely on multiple modality-specific blocks, leaving cross-sensor mismatches unresolved and making fusion unnecessarily complex. Event cameras naturally provide a spatiotemporal edge signal, which we can treat as an intrinsic edge field to anchor a unified latent representation, termed the Event Edge Space. Building on this idea, we introduce x^2-Fusion, which reframes multimodal fusion as representation unification: event-derived spatiotemporal edges define an edge-centric homogeneous space, and image and LiDAR features are explicitly aligned in this shared representation. Within this space, we perform reliability-aware adaptive fusion to estimate modality reliability and emphasize stable cues under degradation. We further employ cross-dimension contrast learning to tightly couple 2D optical flow with 3D scene flow. Extensive experiments on both synthetic and real benchmarks show that x^2-Fusion achieves state-of-the-art accuracy under standard conditions and delivers substantial improvements in challenging scenarios.