# Sketch It Out: Exploring Label-Free Structural Cues for Multimodal Gait Recognition

arXiv: https://arxiv.org/abs/2603.05537 · HTML: https://mlsanity.com/paper/2603.05537/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [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)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [Bi-Directional Cascade Network for Perceptual Edge Detection](https://mlsanity.com/paper/1902.10903/) (2019)
- [Exploring Deep Models for Practical Gait Recognition](https://mlsanity.com/paper/2303.03301/) (2023)
- [Parsing is All You Need for Accurate Gait Recognition in the Wild](https://mlsanity.com/paper/2308.16739/) (2023)
- [Tiny and Efficient Model for the Edge Detection Generalization](https://mlsanity.com/paper/2308.06468/) (2023)
- [CDGNet: Class Distribution Guided Network for Human Parsing](https://mlsanity.com/paper/2111.14173/) (2021)
- [GaitGL: Learning Discriminative Global-Local Feature Representations for Gait Recognition](https://mlsanity.com/paper/2208.01380/) (2022)
- [Deep Learning Technique for Human Parsing: A Survey and Outlook](https://mlsanity.com/paper/2301.00394/) (2023)
- [Gait Recognition in Large-scale Free Environment via Single LiDAR](https://mlsanity.com/paper/2211.12371/) (2022)
- [Exploring More from Multiple Gait Modalities for Human Identification](https://mlsanity.com/paper/2412.11495/) (2024)
- [GaitPT: Skeletons Are All You Need For Gait Recognition](https://mlsanity.com/paper/2308.10623/) (2023)
- [PSGait: Gait Recognition using Parsing Skeleton](https://mlsanity.com/paper/2503.12047/) (2025)
- [TriGait: Aligning and Fusing Skeleton and Silhouette Gait Data via a Tri-Branch Network](https://mlsanity.com/paper/2308.13340/) (2023)

## Abstract (arXiv)

Gait recognition is a non-intrusive biometric technique for security applications, yet existing studies are dominated by silhouette- and parsing-based representations. Silhouettes are sparse and miss internal structural details, limiting discriminability. Parsing enriches silhouettes with part-level structures, but relies heavily on upstream human parsers (e.g., label granularity and boundary precision), leading to unstable performance across datasets and sometimes even inferior results to silhouettes. We revisit gait representations from a structural perspective and describe a design space defined by edge density and supervision form: silhouettes use sparse boundary edges with weak single-label supervision, while parsing uses denser cues with strong semantic priors. In this space, we identify an underexplored paradigm: dense part-level structure without explicit semantic labels, and introduce SKETCH as a new visual modality for gait recognition. Sketch extracts high-frequency structural cues (e.g., limb articulations and self-occlusion contours) directly from RGB images via edge-based detectors in a label-free manner. We further show that label-guided parsing and label-free sketch are semantically decoupled and structurally complementary. Based on this, we propose SKETCHGAIT, a hierarchically disentangled multi-modal framework with two independent streams for modality-specific learning and a lightweight early-stage fusion branch to capture structural complementarity. Extensive experiments on SUSTech1K and CCPG validate the proposed modality and framework: SketchGait achieves 92.9% Rank-1 on SUSTech1K and 93.1% mean Rank-1 on CCPG.