# DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion

arXiv: https://arxiv.org/abs/2606.00153 · HTML: https://mlsanity.com/paper/2606.00153/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 29 May 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 25 of 25)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition](https://mlsanity.com/paper/1811.06186/) (2018)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment](https://mlsanity.com/paper/1910.05839/) (2019)
- [OpenGait: Revisiting Gait Recognition Toward Better Practicality](https://mlsanity.com/paper/2211.06597/) (2022)
- [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023)
- [GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set](https://mlsanity.com/paper/2102.03247/) (2021)
- [LidarGait: Benchmarking 3D Gait Recognition with Point Clouds](https://mlsanity.com/paper/2211.10598/) (2022)
- [A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges](https://mlsanity.com/paper/2206.13732/) (2022)
- [GPGait: Generalized Pose-based Gait Recognition](https://mlsanity.com/paper/2303.05234/) (2023)
- [Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.11708/) (2024)
- [Gait Recognition Based on Deep Learning: A Survey](https://mlsanity.com/paper/2201.03323/) (2022)
- [CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2401.05806/) (2024)
- [Gait Recognition in Large-scale Free Environment via Single LiDAR](https://mlsanity.com/paper/2211.12371/) (2022)
- [OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality](https://mlsanity.com/paper/2405.09138/) (2024)
- [On Denoising Walking Videos for Gait Recognition](https://mlsanity.com/paper/2505.18582/) (2025)
- [Camera-LiDAR Cross-modality Gait Recognition](https://mlsanity.com/paper/2407.02038/) (2024)
- [Cross-Modality Gait Recognition: Bridging LiDAR and Camera Modalities for Human Identification](https://mlsanity.com/paper/2404.04120/) (2024)
- [Diffusion-based Synthetic Data Generation for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2503.12472/) (2025)
- [Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2506.02439/) (2025)
- [Cross-video Identity Correlating for Person Re-identification Pre-training](https://mlsanity.com/paper/2409.18569/) (2024)
- [From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2503.12232/) (2025)
- [CarGait: Cross-Attention based Re-ranking for Gait recognition](https://mlsanity.com/paper/2503.03501/) (2025)

## Abstract (arXiv)

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.