# Multi-Scale Deep Compressive Imaging

arXiv: https://arxiv.org/abs/2008.00802 · HTML: https://mlsanity.com/paper/2008.00802/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2020.

## Built on by (most cited first, 2 of 2)

- [Robust Deep Compressive Sensing with Recurrent-Residual Structural Constraints](https://mlsanity.com/paper/2207.07301/) (2022)
- [Human-Imperceptible Identification with Learnable Lensless Imaging](https://mlsanity.com/paper/2302.02255/) (2023)

## Abstract (arXiv)

Recently, deep learning-based compressive imaging (DCI) has surpassed the conventional compressive imaging in reconstruction quality and faster running time. While multi-scale has shown superior performance over single-scale, research in DCI has been limited to single-scale sampling. Despite training with single-scale images, DCI tends to favor low-frequency components similar to the conventional multi-scale sampling, especially at low subrate. From this perspective, it would be easier for the network to learn multi-scale features with a multi-scale sampling architecture. In this work, we proposed a multi-scale deep compressive imaging (MS-DCI) framework which jointly learns to decompose, sample, and reconstruct images at multi-scale. A three-phase end-to-end training scheme was introduced with an initial and two enhance reconstruction phases to demonstrate the efficiency of multi-scale sampling and further improve the reconstruction performance. We analyzed the decomposition methods (including Pyramid, Wavelet, and Scale-space), sampling matrices, and measurements and showed the empirical benefit of MS-DCI which consistently outperforms both conventional and deep learning-based approaches.