mlsanityData to 14 Oct 2026

From Incomplete Coarse-Grained to Complete Fine-Grained: A Two-Stage Framework for Spatiotemporal Data Reconstruction

arXiv 2410.05323 ↗First posted 5 Oct 2024cs.LG cs.AIcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

With the rapid development of various sensing devices, spatiotemporal data is becoming increasingly important nowadays. However, due to sensing costs and privacy concerns, the collected data is often incomplete and coarse-grained, limiting its application to specific tasks. To address this, we propose a new task called spatiotemporal data reconstruction, which aims to infer complete and fine-grained data from sparse and coarse-grained observations. To achieve this, we introduce a two-stage data inference framework, DiffRecon, grounded in the Denoising Diffusion Probabilistic Model (DDPM). In the first stage, we present Diffusion-C, a diffusion model augmented by ST-PointFormer, a powerful encoder designed to leverage the spatial correlations between sparse data points. Following this, the second stage introduces Diffusion-F, which incorporates the proposed T-PatternNet to capture the temporal pattern within sequential data. Together, these two stages form an end-to-end framework capable of inferring complete, fine-grained data from incomplete and coarse-grained observations. We conducted experiments on multiple real-world datasets to demonstrate the superiority of our method.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 28 of its 42 references that are in the map. First posted on arXiv 5 Oct 2024.

Builds on

28 of 42 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation20 Feb
  2. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul

Other references · 26

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  4. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  5. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  6. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  7. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  8. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  9. 2022Diffusion Models in Vision: A Surveycited by 1,015
  10. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 774
  11. 2018Generative Image Inpainting with Contextual Attentioncited by 580
  12. 2022Diffusion Models for Adversarial Purificationcited by 476
14 more
  1. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 450
  2. 2016Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Predictioncited by 333
  3. 2023One Transformer Fits All Distributions in Multi-Modal Diffusion at Scalecited by 187
  4. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 172
  5. 2023Efficient Diffusion Policies for Offline Reinforcement Learningcited by 157
  6. 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
  7. 2020Joint Air Quality and Weather Prediction Based on Multi-Adversarial Spatiotemporal Networkscited by 39
  8. 2024DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitchingcited by 36
  9. 2019UrbanFM: Inferring Fine-Grained Urban Flowscited by 31
  10. 2022Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Modelscited by 29
  11. 2021Spatial Aggregation and Temporal Convolution Networks for Real-time Krigingcited by 27
  12. 2020Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviorscited by 12
  13. 2020Fine-Grained Urban Flow Inferencecited by 10
  14. 2023Enhance Diffusion to Improve Robust Generalizationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024RDPI: A Refine Diffusion Probability Generation Method for Spatiotemporal Data Imputation
  2. 2024Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse Observations
  3. 2026GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes
  4. 2025Filling the Missings: Spatiotemporal Data Imputation by Conditional Diffusion
  5. 2024Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
  6. 2025Generative Latent Diffusion for Efficient Spatiotemporal Data Reduction
  7. 2026PhysDEM: Physics-Defined Energy-Matching Diffusion for Spatiotemporal Field Generation under Scarce Measurements
  8. 2024A Temporally Disentangled Contrastive Diffusion Model for Spatiotemporal Imputation