2017 IEEE International Conference on Computer Vision (ICCV) 2017
DOI: 10.1109/iccv.2017.517
|View full text |Cite
|
Sign up to set email alerts
|

Deep Generative Adversarial Compression Artifact Removal

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… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

2
98
0
1

Year Published

2018
2018
2020
2020

Publication Types

Select...
5
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 192 publications
(101 citation statements)
references
References 31 publications
2
98
0
1
Order By: Relevance
“…We will also introduce an elaborate joint training, which further improves the rPPG recovery performance. ual denoising neural networks (DnCNN) [37], generative adversarial networks [6] and multi-frame quality enhancement network [36]. However, all of them were designed for solving general compression problems or other tasks like object detection, but not for rPPG measurement.…”
Section: Related Workmentioning
confidence: 99%
“…We will also introduce an elaborate joint training, which further improves the rPPG recovery performance. ual denoising neural networks (DnCNN) [37], generative adversarial networks [6] and multi-frame quality enhancement network [36]. However, all of them were designed for solving general compression problems or other tasks like object detection, but not for rPPG measurement.…”
Section: Related Workmentioning
confidence: 99%
“…Wang et al proposed D3 [12], a deep neural network that adopts JPEG-related priors to improve reconstruction quality which obtained an improvement in speed and performances with respect with to the previous models. In 2017, Galtieri et al [13] developed a generative adversarial network (GAN) [18] for artifact removal and texture reconstruction.…”
Section: Related Workmentioning
confidence: 99%
“…We compared our model with the state-of-the-art models ARCNN [9], CAS-CNN [11], D3 [12], and the more recent DMCNN [15], MWCNN [14], ARGAN [13] and S-Net [16].…”
Section: A Restoration With Known Compression Quality Factormentioning
confidence: 99%
“…Moreover, [7,14,46] enhanced visual quality by exploiting the wavelet/frequency domain information of JPEG compression images. Recently, more methods [1,6,8,12,15,24,27] were proposed and got competitive results. Concretely, Galteri et al [12] used a deep generative adversarial network and recovered more photorealistic details.…”
Section: Single Image Compression Artifact Reductionmentioning
confidence: 99%
“…Recently, more methods [1,6,8,12,15,24,27] were proposed and got competitive results. Concretely, Galteri et al [12] used a deep generative adversarial network and recovered more photorealistic details. Inspired by [39], [24] incorporated non-local operations into a recursive framework for quality restoration, it computed self-similarity between each pixel and its neighbors, and applied the non-local module recursively for correlation propagation.…”
Section: Single Image Compression Artifact Reductionmentioning
confidence: 99%