DiffCrossGait：基于潜在扩散的2D-3D跨模态步态识别轨迹级对齐
DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
AI总结：
针对2D-3D跨模态步态识别中的域差异问题，提出DiffCrossGait，通过潜在扩散空间中的轨迹级对齐实现连续模态对齐，并引入三阶段对齐策略确保身份锚定、动态一致性和跨模态结构可恢复性，在SUSTech1K和FreeGait基准上达到最优性能。
摘要：
跨模态2D-3D步态识别受到2D轮廓和3D LiDAR距离视图表示之间固有域差异的阻碍。虽然先前的方法仅对齐最终嵌入，我们提出DiffCrossGait，将跨模态匹配重新表述为身份相关潜在扩散空间中的轨迹级对齐，而不是假设2D和3D观测完全等价。通过在潜在空间中使用共享高斯噪声驱动两种模态，我们实现了生成演化过程中的连续对齐。我们引入了一种三阶段对齐策略，利用不同的噪声强度来强制身份锚定、动态一致性和跨模态结构可恢复性，从而约束两种模态共享去噪动态和瓶颈结构，促进模态不变的步态特征。关键的是，我们的框架将生成对齐与判别骨干解耦；扩散机制仅作为训练目标，通过消除迭代去噪的计算开销确保高推理效率。在SUSTech1K和FreeGait基准上的大量实验表明，DiffCrossGait达到了最先进的性能。
英文摘要：
Cross-modal 2D-3D gait recognition is impeded by inherent domain discrepancies between 2D silhouette and 3D LiDAR range-view representations. While prior methods align only final embeddings, we propose DiffCrossGait, which reformulates cross-modal matching as trajectory-level alignment in an identity-relevant latent diffusion space, rather than assuming full equivalence between 2D and 3D observations. By driving both modalities with shared Gaussian noise within a latent space, we enable continuous alignment throughout the generative evolution. We introduce a Tri-Phase Alignment Strategy that exploits varying noise intensities to enforce identity anchoring, dynamics consistency, and cross-modal structural recoverability, thereby constraining both modalities to share denoising dynamics and bottleneck structure, which promotes modality-invariant gait features. Crucially, our framework decouples generative alignment from the discriminative backbone; the diffusion mechanism serves exclusively as a training objective, ensuring high inference efficiency by eliminating the computational overhead of iterative denoising. Extensive experiments on the SUSTech1K and FreeGait benchmarks demonstrate that DiffCrossGait achieves state-of-the-art performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
