# Generator Surgery for Compressed Sensing

arXiv: https://arxiv.org/abs/2102.11163 · HTML: https://mlsanity.com/paper/2102.11163/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 19 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 15 of 15)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Compressed Sensing using Generative Models](https://mlsanity.com/paper/1703.03208/) (2017)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [Inverting The Generator Of A Generative Adversarial Network](https://mlsanity.com/paper/1611.05644/) (2016)
- [BEGAN: Boundary Equilibrium Generative Adversarial Networks](https://mlsanity.com/paper/1703.10717/) (2017)
- [Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks](https://mlsanity.com/paper/1810.03982/) (2018)
- [Invertible generative models for inverse problems: mitigating representation error and dataset bias](https://mlsanity.com/paper/1905.11672/) (2019)
- [Image-Adaptive GAN based Reconstruction](https://mlsanity.com/paper/1906.05284/) (2019)
- [Latent Convolutional Models](https://mlsanity.com/paper/1806.06284/) (2018)
- [Reducing the Representation Error of GAN Image Priors Using the Deep Decoder](https://mlsanity.com/paper/2001.08747/) (2020)

## Built on by (most cited first, 5 of 5)

- [Multiresolution Textual Inversion](https://mlsanity.com/paper/2211.17115/) (2022)
- [A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks](https://mlsanity.com/paper/2407.13863/) (2024)
- [Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems](https://mlsanity.com/paper/2206.09104/) (2022)
- [Regularized Training of Intermediate Layers for Generative Models for Inverse Problems](https://mlsanity.com/paper/2203.04382/) (2022)
- [Optimizing Intermediate Representations of Generative Models for Phase Retrieval](https://mlsanity.com/paper/2205.15617/) (2022)

## Abstract (arXiv)

Image recovery from compressive measurements requires a signal prior for the images being reconstructed. Recent work has explored the use of deep generative models with low latent dimension as signal priors for such problems. However, their recovery performance is limited by high representation error. We introduce a method for achieving low representation error using generators as signal priors. Using a pre-trained generator, we remove one or more initial blocks at test time and optimize over the new, higher-dimensional latent space to recover a target image. Experiments demonstrate significantly improved reconstruction quality for a variety of network architectures. This approach also works well for out-of-training-distribution images and is competitive with other state-of-the-art methods. Our experiments show that test-time architectural modifications can greatly improve the recovery quality of generator signal priors for compressed sensing.