Deep Multi-Scale Residual Learning-based Blocking Artifacts Reduction for Compressed Images

Lin, Min-Hui; Yeh, Chia‐Hung; Lin, Chu-Han; Huang, Chih-Hsiang; Kang, Li‐Wei

doi:10.1109/aicas.2019.8771613

Cited by 8 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dong et al [22] was one of the first to use deep learning to solve this very issue. Lin et al [23] more recently also used deep learning techniques that showed improvements in the PSNR of the restored images.…”

Section: Related Workmentioning

confidence: 99%

Removing Blocking Artifacts in Video Streams Using Event Cameras

Chopp¹,

Banerjee²,

Cossairt³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose EveRestNet, a convolutional neural network designed to remove blocking artifacts in video streams using events from neuromorphic sensors. We first degrade the video frame using a quadtree structure to produce the blocking artifacts to simulate transmitting a video under a heavily constrained bandwidth. Events from the neuromorphic sensor are also simulated, but are transmitted in full. Using the distorted frames and the event stream, EveRestNet is able to improve the image quality.

show abstract

Section: Related Workmentioning

confidence: 99%

Removing Blocking Artifacts in Video Streams Using Event Cameras

Chopp¹,

Banerjee²,

Cossairt³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Subsequent methodologies included the use of recursive units and gate units to remove JPEG artifacts [ 18 ], as well as the implementation of a dual-stream multi-path recursive residual network [ 19 ]. Later on, Lin et al [ 20 ] proposed a multiscale image fusion approach to remove JPEG artifacts effectively, and achieved exceptional objective quality. But these methods cannot be extended to compressed video directly, since they treat frames independently and thus fail to exploit temporal information.…”

Section: Introductionmentioning

confidence: 99%

Fast-MFQE: A Fast Approach for Multi-Frame Quality Enhancement on Compressed Video

Chen,

Zeng

et al. 2023

Sensors

View full text Add to dashboard Cite

For compressed images and videos, quality enhancement is essential. Though there have been remarkable achievements related to deep learning, deep learning models are too large to apply to real-time tasks. Therefore, a fast multi-frame quality enhancement method for compressed video, named Fast-MFQE, is proposed to meet the requirement of video-quality enhancement for real-time applications. There are three main modules in this method. One is the image pre-processing building module (IPPB), which is used to reduce redundant information of input images. The second one is the spatio-temporal fusion attention (STFA) module. It is introduced to effectively merge temporal and spatial information of input video frames. The third one is the feature reconstruction network (FRN), which is developed to effectively reconstruct and enhance the spatio-temporal information. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods in terms of lightweight parameters, inference speed, and quality enhancement performance. Even at a resolution of 1080p, the Fast-MFQE achieves a remarkable inference speed of over 25 frames per second, while providing a PSNR increase of 19.6% on average when QP = 37.

show abstract

Anti-forensics for Double JPEG Compression Based on Generative Adversarial Network

Huang

Tang

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Deep Multi-Scale Residual Learning-based Blocking Artifacts Reduction for Compressed Images

Cited by 8 publications

References 12 publications

Removing Blocking Artifacts in Video Streams Using Event Cameras

Removing Blocking Artifacts in Video Streams Using Event Cameras

Fast-MFQE: A Fast Approach for Multi-Frame Quality Enhancement on Compressed Video

Anti-forensics for Double JPEG Compression Based on Generative Adversarial Network

Contact Info

Product

Resources

About