TR2021-003

Generative Patch Priors for Practical Compressive Image Recovery


    •  Anirudh, R., Lohit, S., Turaga, P., "Generative Patch Priors for Practical Compressive Image Recovery", IEEE Winter Conference on Applications of Computer Vision (WACV), January 2021.
      BibTeX TR2021-003 PDF
      • @inproceedings{Anirudh2021jan,
      • author = {Anirudh, Rushil and Lohit, Suhas and Turaga, Pavan},
      • title = {Generative Patch Priors for Practical Compressive Image Recovery},
      • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
      • year = 2021,
      • month = jan,
      • url = {https://www.merl.com/publications/TR2021-003}
      • }
  • MERL Contact:
  • Research Areas:

    Artificial Intelligence, Computer Vision

In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models. Unlike learned, image-level priors that are restricted to the range space of a pre-trained generator, GPP can recover a wide variety of natural images using a pre-trained patch generator. Additionally, GPP retains the benefits of generative priors like high reconstruction quality at extremely low sensing rates, while also being much more generally applicable. We show that GPP outperforms several unsupervised and supervised techniques on three different sensing models – linear compressive sensing with known, and unknown calibration settings, and the non-linear phase retrieval problem. Finally, we propose an alternating optimization strategy using GPP for joint calibration-and-reconstruction which performs favorably against several baselines on a real world, uncalibrated compressive sensing dataset. The code and models for GPP are available on github.