# Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark

arXiv: https://arxiv.org/abs/2603.00611 · HTML: https://mlsanity.com/paper/2603.00611/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 65 references that are in the map.
- First posted on arXiv 28 Feb 2026.

## Builds on (most cited first, 29 of 29)

- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [FLatten Transformer: Vision Transformer using Focused Linear Attention](https://mlsanity.com/paper/2308.00442/) (2023)
- [Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2111.07910/) (2021)
- [Rank Minimization for Snapshot Compressive Imaging](https://mlsanity.com/paper/1807.07837/) (2018)
- [Cross Aggregation Transformer for Image Restoration](https://mlsanity.com/paper/2211.13654/) (2022)
- [Agent Attention: On the Integration of Softmax and Linear Attention](https://mlsanity.com/paper/2312.08874/) (2023)
- [Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging](https://mlsanity.com/paper/2003.13654/) (2020)
- [Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2203.04845/) (2022)
- [HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging](https://mlsanity.com/paper/2203.02149/) (2022)
- [Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging](https://mlsanity.com/paper/2205.10102/) (2022)
- [Video Transformers: A Survey](https://mlsanity.com/paper/2201.05991/) (2022)
- [Bridging the Divide: Reconsidering Softmax and Linear Attention](https://mlsanity.com/paper/2412.06590/) (2024)
- [MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2501.04944/) (2025)
- [Plug-and-Play Algorithms for Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2101.04822/) (2021)
- [Material Based Object Tracking in Hyperspectral Videos: Benchmark and Algorithms](https://mlsanity.com/paper/1812.04179/) (2018)
- [Residual Degradation Learning Unfolding Framework with Mixing Priors across Spectral and Spatial for Compressive Spectral Imaging](https://mlsanity.com/paper/2211.06891/) (2022)
- [Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2308.10820/) (2023)
- [DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification](https://mlsanity.com/paper/2304.09915/) (2023)
- [HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarios](https://mlsanity.com/paper/2409.11205/) (2024)
- [DMSSN: Distilled Mixed Spectral-Spatial Network for Hyperspectral Salient Object Detection](https://mlsanity.com/paper/2404.00694/) (2024)
- [Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation](https://mlsanity.com/paper/2306.08370/) (2023)
- [Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging](https://mlsanity.com/paper/2311.14280/) (2023)
- [Hyperspectral City V1.0 Dataset and Benchmark](https://mlsanity.com/paper/1907.10270/) (2019)
- [Computational Spectral Imaging: A Contemporary Overview](https://mlsanity.com/paper/2303.04848/) (2023)

## Abstract (arXiv)

Recently, Spectral Compressive Imaging (SCI) has achieved remarkable success, unlocking significant potential for dynamic spectral vision. However, existing reconstruction methods, primarily image-based, suffer from two limitations: (i) Encoding process masks spatial-spectral features, leading to uncertainty in reconstructing missing information from single compressed measurements, and (ii) The frame-by-frame reconstruction paradigm fails to ensure temporal consistency, which is crucial in the video perception. To address these challenges, this paper seeks to advance spectral reconstruction from the image level to the video level, leveraging the complementary features and temporal continuity across adjacent frames in dynamic scenes. Initially, we construct the first high-quality dynamic hyperspectral image dataset (DynaSpec), comprising 30 sequences obtained through frame-scanning acquisition. Subsequently, we propose the Propagation-Guided Spectral Video Reconstruction Transformer (PG-SVRT), which employs a spatial-then-temporal attention to effectively reconstruct spectral features from abundant video information, while using a bridged token to reduce computational complexity. Finally, we conduct simulation experiments to assess the performance of four SCI systems, and construct a DD-CASSI prototype for real-world data collection and benchmarking. Extensive experiments demonstrate that PG-SVRT achieves superior performance in reconstruction quality, spectral fidelity, and temporal consistency, while maintaining minimal FLOPs. Project page: https://github.com/nju-cite/DynaSpec