Reduction of Video Compression Artifacts Based on Deep Temporal Networks

Soh, Jae Woong; Park, Jae-Woo; Kim, Yoon-Sik; Ahn, Byeongyong; Lee, Hyunseung; Moon, Yiu Sang; Cho, Nam Ik

doi:10.1109/access.2018.2876864

Cited by 25 publications

(27 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figures 4 and 5 show the subjective quality performance on some test sequences at QP = 42, 37, respectively. By magnifying the images, we can see that our method can better reconstruct visually pleasing results with sharper edges and more texture details than the other methods under comparison, namely, AR-CNN [19], ARTN [23], and MFQE2.0 [24]. The implementations of these methods are all based on their released source codes, and our codes are also available at https://github.com/wgchen-gsu/VCAR-CNN.…”

Section: B Results Of Patch-based Reconstructionmentioning

confidence: 99%

“…The VRCNN can reportedly provide 4.6% BD-rate reduction on average against the HEVC reference implementation. Soh et al [23] proposed a deep artifact reduction temporal network (ARTN) consisting of three temporal branches. One branch takes the current decoded frame, and the other two take the motion compensated frames as input.…”

Section: B Deep Learning For Compression Artifact Reductionmentioning

confidence: 99%

“…In our experiments, the patch size is fixed to be 16 × 16, and the search range is determined in relation to the interval between the current frame and the reference frame. To cope with the case of abrupt scene change, when the matching error exceeds a certain threshold, as in [23], the matching patches are discarded and replaced by the patch in the current frame.…”

Section: Experiments a Datasets And Trainingmentioning

confidence: 99%

“…In particular, for low quality frames, though the trained network may improve their visual quality to some degree, there would always exhibit a large number of visually noticeable artifacts. Therefore, works developed for image sequences typically use multiple frames as the input [23], [24], [26] to the CNN. With the help of its neighboring high-quality frames, a low-quality frame can be adequately enhanced.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Neural Network-Based Video Compression Artifact Reduction Using Temporal Correlation and Sparsity Prior Predictions

Chen

Wang

2020

IEEE Access

View full text Add to dashboard Cite

Quantization in lossy video compression may incur severe quality degradation, especially at low bit-rates. Developing post-processing methods that improve visual quality of decoded images is of great importance, as they can be directly incorporated in any existing compression standard or paradigm. We propose in this paper a two-stage method, a texture detail restoration stage followed by a deep convolutional neural network (CNN) fusion stage, for video compression artifact reduction. The first stage performs in a patch-by-patch manner. For each patch in the current decoded frame, one prediction is formed based on the sparsity prior assuming that natural image patches can be represented by sparse activation of dictionary atoms. Under the temporal correlation hypothesis, we search the best matching patch in each reference frame, and select several matches with more texture details to tile motion compensated predictions. The second stage stacks the predictions obtained in the preceding stage along with the decoded frame itself to form a tensor, and proposes a deep CNN to learn the mapping between the tensor as input and the original uncompressed image as output. Experimental results demonstrate that the proposed two-stage method can remarkably improve, both subjectively and objectively, the quality of the compressed video sequence. INDEX TERMS compression artifact reduction, convolutional neural networks, high efficiency video coding, sparse representation, temporal correlation.

show abstract

Section: B Results Of Patch-based Reconstructionmentioning

confidence: 99%

Section: B Deep Learning For Compression Artifact Reductionmentioning

confidence: 99%

Section: Experiments a Datasets And Trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural Network-Based Video Compression Artifact Reduction Using Temporal Correlation and Sparsity Prior Predictions

Chen

Wang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In many studies, it has been shown that convolution neural network is well known for its capability to control artifacts caused due to JPEG compression; however, it is less discussed that they are not able to handle much more complex artifacts that appears in new compression standards. This problem is addressed in work of Soh et al [39] where the conventional convolution neural network is enhanced by considering the temporal correlational factor obtained from the video file. The presented system claims of addressing artifacts based on directional patterns in HEVC ( Fig.4(a)) and artifacts of blocking in HEVC ( Fig.4(b)).…”

Section: B Typical Machine Learning Approachmentioning

confidence: 99%

Insights on Video Compression Strategies using Machine Learning

Rao

2019

IJEAT

View full text Add to dashboard Cite

With the rising advancement of the multimedia technology, video compression is becoming a challenging problem. Although, there is availability of various standard compression algorithms, yet robust compression performance is yet to be seen in existing compression techniques. This paper also highlights that machine learning plays a significant contributory role in improving the performance of the video compression. Therefore, this manuscript offers a technical insight about the performance of existing video compression technique using machine learning approach. The contribution of this paper is its findings which states that machine learning approach do have significant advantage but the advantageous features are limited by the inherent and unsolved research problem. The core findings of this paper are basically to highlight the strength and limitations of existing methods as well as to highlight the research gap in terms of open-end research problems which requires immediate attention.

show abstract

Deep Feature Fusion Network for Compressed Video Super-Resolution

Wang

et al. 2022

Neural Process Lett

View full text Add to dashboard Cite

Reduction of Video Compression Artifacts Based on Deep Temporal Networks

Cited by 25 publications

References 31 publications

Neural Network-Based Video Compression Artifact Reduction Using Temporal Correlation and Sparsity Prior Predictions

Neural Network-Based Video Compression Artifact Reduction Using Temporal Correlation and Sparsity Prior Predictions

Insights on Video Compression Strategies using Machine Learning

Deep Feature Fusion Network for Compressed Video Super-Resolution

Contact Info

Product

Resources

About