Deep Generative Adversarial Compression Artifact Removal

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

doi:10.1109/iccv.2017.517

Cited by 192 publications

(101 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

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%

Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video Enhancement

Peng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

256

163

View full text Add to dashboard Cite

Remote photoplethysmography (rPPG), which aims at measuring heart activities without any contact, has great potential in many applications (e.g., remote healthcare). Existing rPPG approaches rely on analyzing very fine details of facial videos, which are prone to be affected by video compression. Here we propose a two-stage, endto-end method using hidden rPPG information enhancement and attention networks, which is the first attempt to counter video compression loss and recover rPPG signals from highly compressed videos. The method includes two parts: 1) a Spatio-Temporal Video Enhancement Network (STVEN) for video enhancement, and 2) an rPPG network (rPPGNet) for rPPG signal recovery. The rPPGNet can work on its own for robust rPPG measurement, and the STVEN network can be added and jointly trained to further boost the performance especially on highly compressed videos. Comprehensive experiments are performed on two benchmark datasets to show that, 1) the proposed method not only achieves superior performance on compressed videos with high-quality videos pair, 2) it also generalizes well on novel data with only compressed videos available, which implies the promising potential for realworld applications.

show abstract

Section: Related Workmentioning

confidence: 99%

Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video Enhancement

Peng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

256

163

View full text Add to dashboard Cite

show abstract

“…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%

Deep Residual Autoencoder for Blind Universal JPEG Restoration

2020

View full text Add to dashboard Cite

In this paper we propose a deep residual autoencoder exploiting Residual-in-Residual Dense Blocks (RRDB) to remove artifacts in JPEG compressed images that is independent from the Quality Factor (QF) used. The proposed approach leverages both the learning capacity of deep residual networks and prior knowledge of the JPEG compression pipeline. The proposed model operates in the YCbCr color space and performs JPEG artifact restoration in two phases using two different autoencoders: the first one restores the luma channel exploiting 2D convolutions; the second one, using the restored luma channel as a guide, restores the chroma channels explotining 3D convolutions.Extensive experimental results on three widely used benchmark datasets (i.e. LIVE1, BDS500, and CLASSIC-5) show that our model is able to outperform the state of the art with respect to all the evaluation metrics considered (i.e. PSNR, PSNR-B, and SSIM). This results is remarkable since the approaches in the state of the art use a different set of weights for each compression quality, while the proposed model uses the same weights for all of them, making it applicable to images in the wild where the QF used for compression is unkwnown. Furthermore, the proposed model shows a greater robustness than state-ofthe-art methods when applied to compression qualities not seen during training.

show abstract

“…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%

Non-Local ConvLSTM for Video Compression Artifact Reduction

Gao²,

Tian

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos. Most existing approaches use a single neighboring frame or a pair of neighboring frames (preceding and/or following the target frame) for this task. Furthermore, as frames of high quality overall may contain low-quality patches, and high-quality patches may exist in frames of low quality overall, current methods focusing on nearby peak-quality frames (PQFs) may miss high-quality details in low-quality frames. To remedy these shortcomings, in this paper we propose a novel end-to-end deep neural network called non-local ConvLSTM (NL-ConvLSTM in short) that exploits multiple consecutive frames. An approximate non-local strategy is introduced in NL-ConvLSTM to capture global motion patterns and trace the spatiotemporal dependency in a video sequence. This approximate strategy makes the non-local module work in a fast and low space-cost way. Our method uses the preceding and following frames of the target frame to generate a residual, from which a higher quality frame is reconstructed. Experiments on two datasets show that NL-ConvLSTM outperforms the existing methods.

show abstract

Deep Generative Adversarial Compression Artifact Removal

Cited by 192 publications

References 31 publications

Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video Enhancement

Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video Enhancement

Deep Residual Autoencoder for Blind Universal JPEG Restoration

Non-Local ConvLSTM for Video Compression Artifact Reduction

Contact Info

Product

Resources

About