# RobustSCI: Beyond Reconstruction to Restoration for Snapshot Compressive Imaging under Real-World Degradations

arXiv: https://arxiv.org/abs/2603.07489 · HTML: https://mlsanity.com/paper/2603.07489/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging](https://mlsanity.com/paper/2003.13654/) (2020)
- [Coded aperture compressive temporal imaging](https://mlsanity.com/paper/1302.2575/) (2013)
- [GAP-net for Snapshot Compressive Imaging](https://mlsanity.com/paper/2012.08364/) (2020)
- [DarkIR: Robust Low-Light Image Restoration](https://mlsanity.com/paper/2412.13443/) (2024)
- [Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging](https://mlsanity.com/paper/2109.06548/) (2021)
- [Memory-Efficient Network for Large-scale Video Compressive Sensing](https://mlsanity.com/paper/2103.03089/) (2021)
- [MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing](https://mlsanity.com/paper/2103.01786/) (2021)
- [Low-Cost Compressive Sensing for Color Video and Depth](https://mlsanity.com/paper/1402.6932/) (2014)
- [EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2305.10006/) (2023)
- [Adaptive Deep PnP Algorithm for Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2201.05483/) (2022)
- [MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2410.14214/) (2024)
- [Spectral Compressive Imaging Reconstruction Using Convolution and Contextual Transformer](https://mlsanity.com/paper/2201.05768/) (2022)
- [Hierarchical Separable Video Transformer for Snapshot Compressive Imaging](https://mlsanity.com/paper/2407.11946/) (2024)
- [Event-Enhanced Snapshot Compressive Videography at 10K FPS](https://mlsanity.com/paper/2404.07551/) (2024)

## Abstract (arXiv)

Deep learning algorithms for video Snapshot Compressive Imaging (SCI) have achieved great success, yet they predominantly focus on reconstructing from clean measurements. This overlooks a critical real-world challenge: the captured signal itself is often severely degraded by motion blur and low light. Consequently, existing models falter in practical applications. To break this limitation, we pioneer the first study on robust video SCI restoration, shifting the goal from "reconstruction" to "restoration"--recovering the underlying pristine scene from a degraded measurement. To facilitate this new task, we first construct a large-scale benchmark by simulating realistic, continuous degradations on the DAVIS 2017 dataset. Second, we propose RobustSCI, a network that enhances a strong encoder-decoder backbone with a novel RobustCFormer block. This block introduces two parallel branches--a multi-scale deblur branch and a frequency enhancement branch--to explicitly disentangle and remove degradations during the recovery process. Furthermore, we introduce RobustSCI-C (RobustSCI-Cascade), which integrates a pre-trained Lightweight Post-processing Deblurring Network to significantly boost restoration performance with minimal overhead. Extensive experiments demonstrate that our methods outperform all SOTA models on the new degraded testbeds, with additional validation on real-world degraded SCI data confirming their practical effectiveness, elevating SCI from merely reconstructing what is captured to restoring what truly happened.