# DIFFUMA: High-Fidelity Spatio-Temporal Video Prediction via Dual-Path Mamba and Diffusion Enhancement

arXiv: https://arxiv.org/abs/2507.06738 · HTML: https://mlsanity.com/paper/2507.06738/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 30 of 31)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [Structured Sequence Modeling with Graph Convolutional Recurrent Networks](https://mlsanity.com/paper/1612.07659/) (2016)
- [WeatherBench: A benchmark dataset for data-driven weather forecasting](https://mlsanity.com/paper/2002.00469/) (2020)
- [Earthformer: Exploring Space-Time Transformers for Earth System Forecasting](https://mlsanity.com/paper/2207.05833/) (2022)
- [Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey](https://mlsanity.com/paper/2303.14483/) (2023)
- [PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning](https://mlsanity.com/paper/1804.06300/) (2018)
- [Flowformer: Linearizing Transformers with Conservation Flows](https://mlsanity.com/paper/2202.06258/) (2022)
- [A Survey on Diffusion Models for Time Series and Spatio-Temporal Data](https://mlsanity.com/paper/2404.18886/) (2024)
- [Transformers in Remote Sensing: A Survey](https://mlsanity.com/paper/2209.01206/) (2022)
- [PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction](https://mlsanity.com/paper/2305.11421/) (2023)
- [Graph Transformers: A Survey](https://mlsanity.com/paper/2407.09777/) (2024)
- [Graph Neural Processes for Spatio-Temporal Extrapolation](https://mlsanity.com/paper/2305.18719/) (2023)
- [Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias](https://mlsanity.com/paper/2505.19038/) (2025)
- [Advanced Long-term Earth System Forecasting](https://mlsanity.com/paper/2505.19432/) (2025)

## Abstract (arXiv)

Spatio-temporal video prediction plays a pivotal role in critical domains, ranging from weather forecasting to industrial automation. However, in high-precision industrial scenarios such as semiconductor manufacturing, the absence of specialized benchmark datasets severely hampers research on modeling and predicting complex processes. To address this challenge, we make a twofold contribution.First, we construct and release the Chip Dicing Lane Dataset (CHDL), the first public temporal image dataset dedicated to the semiconductor wafer dicing process. Captured via an industrial-grade vision system, CHDL provides a much-needed and challenging benchmark for high-fidelity process modeling, defect detection, and digital twin development.Second, we propose DIFFUMA, an innovative dual-path prediction architecture specifically designed for such fine-grained dynamics. The model captures global long-range temporal context through a parallel Mamba module, while simultaneously leveraging a diffusion module, guided by temporal features, to restore and enhance fine-grained spatial details, effectively combating feature degradation. Experiments demonstrate that on our CHDL benchmark, DIFFUMA significantly outperforms existing methods, reducing the Mean Squared Error (MSE) by 39% and improving the Structural Similarity (SSIM) from 0.926 to a near-perfect 0.988. This superior performance also generalizes to natural phenomena datasets. Our work not only delivers a new state-of-the-art (SOTA) model but, more importantly, provides the community with an invaluable data resource to drive future research in industrial AI.