# BoundInk: Boundary-Aware Online Handwriting Generation

arXiv: https://arxiv.org/abs/2604.02103 · HTML: https://mlsanity.com/paper/2604.02103/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images](https://mlsanity.com/paper/2003.02567/) (2020)
- [Handwriting Transformers](https://mlsanity.com/paper/2104.03964/) (2021)
- [Disentangling Writer and Character Styles for Handwriting Generation](https://mlsanity.com/paper/2303.14736/) (2023)
- [Drawing and Recognizing Chinese Characters with Recurrent Neural Network](https://mlsanity.com/paper/1606.06539/) (2016)
- [DeepWriteSYN: On-Line Handwriting Synthesis via Deep Short-Term Representations](https://mlsanity.com/paper/2009.06308/) (2020)
- [SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text](https://mlsanity.com/paper/2202.11456/) (2022)
- [Generating Handwriting via Decoupled Style Descriptors](https://mlsanity.com/paper/2008.11354/) (2020)
- [Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens](https://mlsanity.com/paper/2202.07036/) (2022)
- [Online handwriting, signature and touch dynamics: tasks and potential applications in the field of security and health](https://mlsanity.com/paper/2202.12693/) (2022)
- [Decoupling Layout from Glyph in Online Chinese Handwriting Generation](https://mlsanity.com/paper/2410.02309/) (2024)
- [Character Queries: A Transformer-based Approach to On-Line Handwritten Character Segmentation](https://mlsanity.com/paper/2309.03072/) (2023)
- [TrInk: Ink Generation with Transformer Network](https://mlsanity.com/paper/2508.21098/) (2025)
- [Learning to Kern: Set-wise Estimation of Optimal Letter Space](https://mlsanity.com/paper/2402.14313/) (2024)

## Abstract (arXiv)

Realistic online handwriting depends not only on individual character shapes, but also on how a writer connects, spaces, and aligns adjacent characters. Existing methods rely primarily on long-range sequence modeling and capture these inter-character behaviors only implicitly. This often produces plausible glyphs accompanied by broken cursive joins, inconsistent spacing, or writer-inconsistent transitions. We introduce BoundInk, a writer-conditioned framework that treats inter-character boundaries as explicit generation units. By jointly modeling local transitions and surrounding text context, BoundInk preserves writer-specific glyph appearance while improving connectivity and spacing across complete text lines. We further introduce a boundary-aware evaluation framework that directly assesses cursive continuity and spatial relationships between characters beyond conventional trajectory similarity. Across three benchmark-matched settings, BoundInk improves all applicable boundary-quality measures and reduces normalized dynamic time warping by 17.6--47.8%. In blind human evaluations, BoundInk outputs are preferred in 78.0--82.6% of valid criterion-wise judgments.