# On Denoising Walking Videos for Gait Recognition

arXiv: https://arxiv.org/abs/2505.18582 · HTML: https://mlsanity.com/paper/2505.18582/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 68 references that are in the map.
- First posted on arXiv 24 May 2025.

## Builds on (most cited first, 30 of 45)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Text-to-Image Diffusion Models are Zero-Shot Classifiers](https://mlsanity.com/paper/2303.15233/) (2023)
- [Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion](https://mlsanity.com/paper/2308.12469/) (2023)
- [Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation](https://mlsanity.com/paper/2011.01461/) (2020)
- [GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition](https://mlsanity.com/paper/2101.11228/) (2021)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [Diffusion Model as Representation Learner](https://mlsanity.com/paper/2308.10916/) (2023)
- [OpenGait: Revisiting Gait Recognition Toward Better Practicality](https://mlsanity.com/paper/2211.06597/) (2022)
- [VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation](https://mlsanity.com/paper/2303.08340/) (2023)
- [Appearance-Preserving 3D Convolution for Video-based Person Re-identification](https://mlsanity.com/paper/2007.08434/) (2020)
- [GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set](https://mlsanity.com/paper/2102.03247/) (2021)
- [Towards a Deeper Understanding of Skeleton-based Gait Recognition](https://mlsanity.com/paper/2204.07855/) (2022)
- [LidarGait: Benchmarking 3D Gait Recognition with Point Clouds](https://mlsanity.com/paper/2211.10598/) (2022)
- [GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality](https://mlsanity.com/paper/2203.03972/) (2022)
- [Exploring Deep Models for Practical Gait Recognition](https://mlsanity.com/paper/2303.03301/) (2023)
- [A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges](https://mlsanity.com/paper/2206.13732/) (2022)
- [BigGait: Learning Gait Representation You Want by Large Vision Models](https://mlsanity.com/paper/2402.19122/) (2024)
- [On Learning Disentangled Representations for Gait Recognition](https://mlsanity.com/paper/1909.03051/) (2019)
- [SkeletonGait: Gait Recognition Using Skeleton Maps](https://mlsanity.com/paper/2311.13444/) (2023)

## Built on by (most cited first, 14 of 14)

- [LocalScore: Local Density-Aware Similarity Scoring for Biometrics](https://mlsanity.com/paper/2602.01012/) (2026)
- [Silhouette-based Gait Foundation Model](https://mlsanity.com/paper/2512.00691/) (2025)
- [EventGait: Towards Robust Gait Recognition with Event Streams](https://mlsanity.com/paper/2605.22139/) (2026)
- [Gait Recognition via Collaborating Discriminative and Generative Diffusion Models](https://mlsanity.com/paper/2511.06245/) (2025)
- [GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition](https://mlsanity.com/paper/2604.26255/) (2026)
- [Text-guided Feature Disentanglement for Cross-modal Gait Recognition](https://mlsanity.com/paper/2605.30784/) (2026)
- [MHRGait: Gait Recognition from Momentum Human Rig Pose](https://mlsanity.com/paper/2607.29083/) (2026)
- [Decoding Children's Gait Behavior](https://mlsanity.com/paper/2608.00371/) (2026)
- [SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception](https://mlsanity.com/paper/2608.10497/) (2026)
- [Human Identification at a Distance: Challenges, Methods and Results on the Competition HID 2025](https://mlsanity.com/paper/2602.07565/) (2026)
- [BarbieGait: An Identity-Consistent Synthetic Human Dataset with Versatile Cloth-Changing for Gait Recognition](https://mlsanity.com/paper/2604.12221/) (2026)
- [DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion](https://mlsanity.com/paper/2606.00153/) (2026)
- [Adaptive Causal Alignment for High-Confidence Adversarial Training](https://mlsanity.com/paper/2606.03925/) (2026)
- [LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba](https://mlsanity.com/paper/2609.24337/) (2026)

## Abstract (arXiv)

To capture individual gait patterns, excluding identity-irrelevant cues in walking videos, such as clothing texture and color, remains a persistent challenge for vision-based gait recognition. Traditional silhouette- and pose-based methods, though theoretically effective at removing such distractions, often fall short of high accuracy due to their sparse and less informative inputs. Emerging end-to-end methods address this by directly denoising RGB videos using human priors. Building on this trend, we propose DenoisingGait, a novel gait denoising method. Inspired by the philosophy that "what I cannot create, I do not understand", we turn to generative diffusion models, uncovering how they partially filter out irrelevant factors for gait understanding. Additionally, we introduce a geometry-driven Feature Matching module, which, combined with background removal via human silhouettes, condenses the multi-channel diffusion features at each foreground pixel into a two-channel direction vector. Specifically, the proposed within- and cross-frame matching respectively capture the local vectorized structures of gait appearance and motion, producing a novel flow-like gait representation termed Gait Feature Field, which further reduces residual noise in diffusion features. Experiments on the CCPG, CASIA-B*, and SUSTech1K datasets demonstrate that DenoisingGait achieves a new SoTA performance in most cases for both within- and cross-domain evaluations. Code is available at https://github.com/ShiqiYu/OpenGait.