Self-Supervised Diffusion Models for Handwritten Signature Verification via Ruin Reconstruction
cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Handwritten signature verification (HSV) is a critical biometric technique in legal and forensic authentication, whose efficacy hinges on the discriminability of signature representations.
Terminology
Abstract
Handwritten signature verification (HSV) is a critical biometric technique in legal and forensic authentication, whose efficacy hinges on the discriminability of signature representations. Current HSV methods predominantly adopt supervised learning to enhance representation quality, leaving self-supervised learning largely unexplored. We propose SigDiffuser, a diffusion-based self-supervised framework for signature representation and verification. At its core, SigDiffuser introduces a novel pretext task termed Reconstruction from Ruins (RFR), which deliberately ``ruins'' signatures through severe crumpling, obliterating their structural integrity and writing styles. A visual encoder is employed to capture crucial handwriting patterns from intact signature regions, guiding the denoiser to reconstruct the ``ruined'' portions and learning meaningful representations. Additionally, we introduce a pyramidal feature aggregation module (PFAM) to bridge the visual encoder and denoiser, enhancing representation quality via hierarchical aggregation and modulation. Extensive experiments on multilingual signature datasets demonstrate that SigDiffuser significantly outperforms both state-of-the-art SSL methods and HSV models. We further show that increasing the crumpling severity on signatures effectively improves representation quality. Notably, our work demonstrates that extreme destruction, coupled with self-supervised diffusion models, can yield superior signature representation compared to traditional mild deformations, paving new avenues for HSV and other biometric domains. Code will be publicly available.
Sources
- Multiscale Feature Learning Using Co-Tuplet Loss for Offline Handwritten Signature Verification
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification
- Improved Baselines with Momentum Contrastive Learning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs