# MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing

arXiv: https://arxiv.org/abs/2103.01786 · HTML: https://mlsanity.com/paper/2103.01786/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 45 references that are in the map.
- First posted on arXiv 2 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [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)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Rank Minimization for Snapshot Compressive Imaging](https://mlsanity.com/paper/1807.07837/) (2018)
- [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)
- [Plug-and-Play Algorithms for Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2101.04822/) (2021)
- [Low-Cost Compressive Sensing for Color Video and Depth](https://mlsanity.com/paper/1402.6932/) (2014)
- [DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensing](https://mlsanity.com/paper/1607.03343/) (2016)
- [Compressive Hyperspectral Imaging with Side Information](https://mlsanity.com/paper/1502.06260/) (2015)
- [Deep Fully-Connected Networks for Video Compressive Sensing](https://mlsanity.com/paper/1603.04930/) (2016)

## Built on by (most cited first, 29 of 29)

- [Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging](https://mlsanity.com/paper/2108.12654/) (2021)
- [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)
- [Spatial-Temporal Transformer for Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2209.01578/) (2022)
- [EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2305.10006/) (2023)
- [SoDaCam: Software-defined Cameras via Single-Photon Imaging](https://mlsanity.com/paper/2309.00066/) (2023)
- [TransCL: Transformer Makes Strong and Flexible Compressive Learning](https://mlsanity.com/paper/2207.11972/) (2022)
- [Deep Optics for Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2404.05274/) (2024)
- [Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision](https://mlsanity.com/paper/2109.08880/) (2021)
- [Deep Equilibrium Models for Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2201.06931/) (2022)
- [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)
- [Two-Stage is Enough: A Concise Deep Unfolding Reconstruction Network for Flexible Video Compressive Sensing](https://mlsanity.com/paper/2201.05810/) (2022)
- [SCINeRF: Neural Radiance Fields from a Snapshot Compressive Image](https://mlsanity.com/paper/2403.20018/) (2024)
- [10-mega pixel snapshot compressive imaging with a hybrid coded aperture](https://mlsanity.com/paper/2106.15765/) (2021)
- [Revisit Dictionary Learning for Video Compressive Sensing under the Plug-and-Play Framework](https://mlsanity.com/paper/2110.04966/) (2021)
- [Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2306.11316/) (2023)
- [Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworks](https://mlsanity.com/paper/2307.06771/) (2023)
- [SnapCap: Efficient Snapshot Compressive Video Captioning](https://mlsanity.com/paper/2401.04903/) (2024)
- [Event-Enhanced Snapshot Compressive Videography at 10K FPS](https://mlsanity.com/paper/2404.07551/) (2024)
- [Reinforcement Learning for Adaptive Video Compressive Sensing](https://mlsanity.com/paper/2105.08205/) (2021)
- [Motion-aware Dynamic Graph Neural Network for Video Compressive Sensing](https://mlsanity.com/paper/2203.00387/) (2022)
- [Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms](https://mlsanity.com/paper/2406.03694/) (2024)
- [Towards Real-time Video Compressive Sensing on Mobile Devices](https://mlsanity.com/paper/2408.07530/) (2024)
- [Snapshot Compressive Imaging: Principle, Implementation, Theory, Algorithms and Applications](https://mlsanity.com/paper/2103.04421/) (2021)
- [Hierarchical Interactive Reconstruction Network For Video Compressive Sensing](https://mlsanity.com/paper/2304.07473/) (2023)
- [Sparse Transformer for Ultra-sparse Sampled Video Compressive Sensing](https://mlsanity.com/paper/2509.08228/) (2025)
- [3One2: One-step Regression Plus One-step Diffusion for One-hot Modulation in Dual-path Video Snapshot Compressive Imaging](https://mlsanity.com/paper/2512.17578/) (2025)
- [RobustSCI: Beyond Reconstruction to Restoration for Snapshot Compressive Imaging under Real-World Degradations](https://mlsanity.com/paper/2603.07489/) (2026)

## Abstract (arXiv)

To capture high-speed videos using a two-dimensional detector, video snapshot compressive imaging (SCI) is a promising system, where the video frames are coded by different masks and then compressed to a snapshot measurement. Following this, efficient algorithms are desired to reconstruct the high-speed frames, where the state-of-the-art results are achieved by deep learning networks. However, these networks are usually trained for specific small-scale masks and often have high demands of training time and GPU memory, which are hence bf em not flexible to i) a new mask with the same size and ii) a larger-scale mask. We address these challenges by developing a Meta Modulated Convolutional Network for SCI reconstruction, dubbed MetaSCI. MetaSCI is composed of a shared backbone for different masks, and light-weight meta-modulation parameters to evolve to different modulation parameters for each mask, thus having the properties of bf em fast adaptation to new masks (or systems) and ready to bf em scale to large data. Extensive simulation and real data results demonstrate the superior performance of our proposed approach. Our code is available at smallurlhttps://github.com/xyvirtualgroup/MetaSCI-CVPR2021.