Compression artifacts arise in images whenever a lossy compression algorithm is applied. These artifacts eliminate details present in the original image, or add noise and small structures; because of these effects they make images less pleasant for the human eye, and may also lead to decreased performance of computer vision algorithms such as object detectors. To eliminate such artifacts, when decompressing an image, it is required to recover the original image from a disturbed version. To this end, we present a feed-forward fully convolutional residual network model that directly optimizes the Structural Similarity (SSIM), which is a better loss with respect to the simpler Mean Squared Error (MSE). We then build on the same architecture to re-formulate the problem in a generative adversarial framework. Our GAN is able to produce images with more photorealistic details than MSE or SSIM based networks. Moreover we show that our approach can be used as a pre-processing step for object detection in case images are degraded by compression to a point that state-of-the art detectors fail. In this task, our GAN method obtains better performance than MSE or SSIM trained networks.

Deep Generative Adversarial Compression Artifact Removal / Leonardo, Galteri; Lorenzo, Seidenari; Marco, Bertini; Alberto Del, Bimbo. - ELETTRONICO. - (2017), pp. 4826-4835. (Intervento presentato al convegno International Conference on Computer Vision tenutosi a Venezia nel 22-29 October) [10.1109/ICCV.2017.517].

Deep Generative Adversarial Compression Artifact Removal

Leonardo, Galteri;Lorenzo, Seidenari;Marco, Bertini;Alberto Del, Bimbo
2017

Abstract

Compression artifacts arise in images whenever a lossy compression algorithm is applied. These artifacts eliminate details present in the original image, or add noise and small structures; because of these effects they make images less pleasant for the human eye, and may also lead to decreased performance of computer vision algorithms such as object detectors. To eliminate such artifacts, when decompressing an image, it is required to recover the original image from a disturbed version. To this end, we present a feed-forward fully convolutional residual network model that directly optimizes the Structural Similarity (SSIM), which is a better loss with respect to the simpler Mean Squared Error (MSE). We then build on the same architecture to re-formulate the problem in a generative adversarial framework. Our GAN is able to produce images with more photorealistic details than MSE or SSIM based networks. Moreover we show that our approach can be used as a pre-processing step for object detection in case images are degraded by compression to a point that state-of-the art detectors fail. In this task, our GAN method obtains better performance than MSE or SSIM trained networks.
2017
Proc. of IEEE International Conference on Computer Vision (ICCV)
International Conference on Computer Vision
Venezia
22-29 October
Leonardo, Galteri; Lorenzo, Seidenari; Marco, Bertini; Alberto Del, Bimbo
File in questo prodotto:
File Dimensione Formato  
PID4924893.pdf

Accesso chiuso

Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: Tutti i diritti riservati
Dimensione 3.94 MB
Formato Adobe PDF
3.94 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1094138
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 147
  • ???jsp.display-item.citation.isi??? 128
social impact