Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC

Ki, Sehwan; Do, Jeonghyeok; Kim, Munchurl

doi:10.1109/access.2020.3046194

Cited by 9 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The above network is trained once for the QP27 case and applied to other QPs. On the contrary, in HDR-JNDNet [17], Ki et al generate the training data and train the JND prefiltering network for each QP individually, which is time-consuming and inconvenient for practical use. In this work, from our experiences, we found that the best scale for the same area will be similar in the IQA-guided selection under different QPs, which implies that we could train only one model in the base QP and apply it on different QPs directly.…”

Section: B Model Consideration For Different Qpsmentioning

confidence: 99%

“…With this, they trained a CNN-based JND prefiltering model with a one-QP one-model approach for different QPs, called CNN-JNQD. They also extended ERJND and applied it to HDR video (HDR-JNDNet) [17]. However, their 8x8 block-based method could lead to blocking effects.…”

Section: Introductionmentioning

confidence: 99%

“…The same magnitude reduction for all frequency bands does not fit the human visual system well. Their model has 14 layers [17], which will require high computational complexity for current high-definition video inputs. The one-QP one-model approach is not convenient for practical use.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering for Versatile Video Coding

Sun,

Lee,

Chang

2024

IEEE Open J. Circuits Syst.

View full text Add to dashboard Cite

Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant information prior to compression. However, real JND cannot be well modeled with inaccurate masking equations in traditional approaches or imagelevel subject tests in deep learning approaches. Thus, this paper proposes a fine-grained JND prefiltering dataset guided by image quality assessment for accurate block-level JND modeling. The dataset is constructed from decoded images to include coding effects and is also perceptually enhanced with block overlap and edge preservation. Furthermore, based on this dataset, we propose a lightweight JND prefiltering network, IQNet, which can be applied directly to different quantization cases with the same model and only needs 3K parameters. The experimental results show that the proposed approach to Versatile Video Coding could yield maximum/average bitrate savings of 41%/15% and 53%/19% for all-intra and low-delay P configurations, respectively, with negligible subjective quality loss. Our method demonstrates higher perceptual quality and a model size that is an order of magnitude smaller than previous deep learning methods.

show abstract

Section: B Model Consideration For Different Qpsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering for Versatile Video Coding

Sun,

Lee,

Chang

2024

IEEE Open J. Circuits Syst.

View full text Add to dashboard Cite

show abstract

“…First, we use a multiprocess to improve the average response time and calculate the number of pictures cut out of the video at the speed of 30 fps. Then, based on equal difference sampling, the tolerance is calculated when the cardinality is fixed, and the image is selected from the starting frame [30]. Through isometric selection, we not only obtain the core motion information of sign language, but also reduce the dataset and the impact of unnecessary data on the experiment.…”

Section: Rgb Video Preprocessingmentioning

confidence: 99%

“…Each image is converted into a feature vector of [1,512]. The 30 images are combined into a temporal feature vector [30,1,1512], which is then used as the input of the Bi-LSTM network. The initial learning rate is 0.001, and the CrossEntropy loss is used.…”

Section: Network Pre-trainingmentioning

confidence: 99%

Dynamic Sign Language Recognition Based on CBAM with Autoencoder Time Series Neural Network

Huang

Xiao-yue

et al. 2022

Mobile Information Systems

View full text Add to dashboard Cite

The CNN-LSTM network has a low generalization ability, and the backward relevance of actions is not strong. In this work, a convolutional self-encoding timing network with a fusion of attention mechanism, namely, convolutional block attention module (CBAM), is proposed. The model first designs a convolutional self-encoding network for pretraining to obtain feature vectors of smaller dimensions. Second, it uses the BN network to speed up the training process and enhance the network generalization ability. Then, we use the encoder part of the pretrained convolutional autoencoder, embed the attention mechanism to further focus on the weight of important parts in image features, and use Bi-LSTM to form a CNN-Bi-LSTM network. As compared with the traditional CNN-LSTM model, the proposed method continuously expands the training samples through the pretrained network to improve the generalization performance. The experimental results show that the method proposed in this paper effectively recognizes the sign language video. The recognition rate reaches 89.90%, which is higher as compared to other methods. These results verify the feasibility and effectiveness of the proposed method.

show abstract

HDR Video Coding Based on Perceptual Optimization

Sun,

Zhu,

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC

Cited by 9 publications

References 21 publications

IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering for Versatile Video Coding

IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering for Versatile Video Coding

Dynamic Sign Language Recognition Based on CBAM with Autoencoder Time Series Neural Network

HDR Video Coding Based on Perceptual Optimization

Contact Info

Product

Resources

About