# A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking

arXiv: https://arxiv.org/abs/2510.06699 · HTML: https://mlsanity.com/paper/2510.06699/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 42 of its 63 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 30 of 42)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Neural Controlled Differential Equations for Irregular Time Series](https://mlsanity.com/paper/2005.08926/) (2020)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2101.12072/) (2021)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Modeling Irregular Time Series with Continuous Recurrent Units](https://mlsanity.com/paper/2111.11344/) (2021)
- [Imaging Time-Series to Improve Classification and Imputation](https://mlsanity.com/paper/1506.00327/) (2015)
- [Time Series as Images: Vision Transformer for Irregularly Sampled Time Series](https://mlsanity.com/paper/2303.12799/) (2023)
- [ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling](https://mlsanity.com/paper/2402.10635/) (2024)
- [PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series](https://mlsanity.com/paper/2108.00981/) (2021)
- [On the Constrained Time-Series Generation Problem](https://mlsanity.com/paper/2307.01717/) (2023)
- [Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs](https://mlsanity.com/paper/2310.02619/) (2023)
- [GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/2210.02040/) (2022)

## Built on by (most cited first, 7 of 7)

- [WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation](https://mlsanity.com/paper/2510.11839/) (2025)
- [Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge](https://mlsanity.com/paper/2510.20819/) (2025)
- [XCTFormer: Leveraging Cross-Channel and Cross-Time Dependencies for Enhanced Time-Series Analysis](https://mlsanity.com/paper/2605.18534/) (2026)
- [TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation](https://mlsanity.com/paper/2606.07569/) (2026)
- [Discretizing Continuous Time Series for Imputation with Masked Diffusion Training](https://mlsanity.com/paper/2608.19119/) (2026)
- [CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation](https://mlsanity.com/paper/2609.27825/) (2026)
- [ChronoFlow: Hierarchical Flow Matching for Irregular Time Series Generation](https://mlsanity.com/paper/2609.33276/) (2026)

## Abstract (arXiv)

Generating realistic time series data is critical for applications in healthcare, finance, and science. However, irregular sampling and missing values present significant challenges. While prior methods address these irregularities, they often yield suboptimal results and incur high computational costs. Recent advances in regular time series generation, such as the diffusion-based ImagenTime model, demonstrate strong, fast, and scalable generative capabilities by transforming time series into image representations, making them a promising solution. However, extending ImagenTime to irregular sequences using simple masking introduces "unnatural" neighborhoods, where missing values replaced by zeros disrupt the learning process. To overcome this, we propose a novel two-step framework: first, a Time Series Transformer completes irregular sequences, creating natural neighborhoods; second, a vision-based diffusion model with masking minimizes dependence on the completed values. This approach leverages the strengths of both completion and masking, enabling robust and efficient generation of realistic time series. Our method achieves state-of-the-art performance, achieving a relative improvement in discriminative score by 70% and in computational cost by 85%. Code is at https://github.com/azencot-group/ImagenI2R.