DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Cross-modal Gait Recognition | FreeGait (test) | Rank-1 Accuracy61.5 | 28 | |
| Gait Recognition | SUSTech1K 3D LiDAR → 2D Camera | Rank-1 Accuracy (Overall)63.8 | 14 | |
| Cross-modal Gait Recognition | SUSTech 2D Camera → 3D LiDAR 1K (test) | Overall Rank-1 Acc58.7 | 10 |