Temporal fluctuation artifact is often observed in digitally compressed video. However, the fluctuation intensity cannot be correctly measured by the traditional image/video quality metric, e.g., the peak signal-to-no...
详细信息
ISBN:
(纸本)9780819482341
Temporal fluctuation artifact is often observed in digitally compressed video. However, the fluctuation intensity cannot be correctly measured by the traditional image/video quality metric, e.g., the peak signal-to-noise ratio (PSNR), which only addresses on the quality of a single image. Although there are several metrics proposed for temporal fluctuation measurement, e.g., the sum of squared differences (SSD) and motion compensated SSD (MCSSD), these first difference based algorithms may falsely treat a smoothly continuous change of pixels as the temporal fluctuation artifact. To overcome this problem, this contribution proposes a second difference based temporal metric, named the motion estimated mean scaled absolute second difference (MEMSASD). The performance of the MEMSASD is examined using a number of video sequences with varying degrees of temporal fluctuation, which are generated by an H.264/AVC compliant codec. Compared with existing metrics such as the PSNR, the SSD and the MCSSD, the results of the proposed metric better reflect the temporal fluctuation intensity.
We previously proposed a machine learning based post filtering method for reducing image artifacts caused by lossy compression. The method classifies reconstructed image samples into three categories using a support v...
详细信息
ISBN:
(数字)9781510627741
ISBN:
(纸本)9781510627741
We previously proposed a machine learning based post filtering method for reducing image artifacts caused by lossy compression. The method classifies reconstructed image samples into three categories using a support vector machine (SVM) to roughly discriminate magnitude of the reconstruction errors. Then, an optimum offset value is added to the samples belonging to each category in a similar way to the post filtering technique called sample adaptive offset (SAO) used in the H.265/HEVC standard. In this paper, two kinds of SVM classifiers are adaptively switched according to information on block boundaries of transform units (TUs) in H.265/HEVC intra-frame coding. Furthermore, samples used for a feature vector, which will be fed to the SVM classifier, are rotated at the block boundary to properly capture local characteristics of the reconstruction errors.
The paper proposes a novel algorithm to enhance the quality of H.264/AVC compressed video sequences by using an in-loop spatio-temporal motion compensated filter (MCSTF). Extra information from surrounding coded frame...
详细信息
ISBN:
(纸本)9781424456536
The paper proposes a novel algorithm to enhance the quality of H.264/AVC compressed video sequences by using an in-loop spatio-temporal motion compensated filter (MCSTF). Extra information from surrounding coded frames are used together with the information of the current coded frame to reduce the coding artifacts. With the availability of the original frame, the MCSTF coefficients are optimized at the encoder and then are implemented at the decoder. Furthermore, an overlapped motion compensated scheme is proposed to reduce the blocking artifacts from surrounding motion compensated frames. Simulation results are judged by PSNR and flickering metric.
An iterative postprocessing algorithm is proposed in the paper to reduce the coding artifacts produced by block based motion compensated transform coding. In the proposed approach, the adaptive spatial operations foll...
详细信息
ISBN:
(纸本)0818669527
An iterative postprocessing algorithm is proposed in the paper to reduce the coding artifacts produced by block based motion compensated transform coding. In the proposed approach, the adaptive spatial operations followed by the adaptive motion compensated temporal operation are applied to the reconstructed image iteratively. As both the spatial and the temporal operations are adaptive to the image contents in both the spatial and the temporal domain, iteratively applying those operations to the reconstructed image can greatly reduce the coding artifacts without blurring image details. The computer simulations show that by using the proposed algorithm, one can reduce the coding artifacts and improve the quality of the reconstructed image effectively.
As the upcoming video coding standard, VersatileVideo coding (i.e., VVC) achieves up to 30% Bjontegaard delta bit-rate (BD-rate) reduction compared with High EfficiencyVideo coding (H.265/HEVC). To eliminate or allevi...
详细信息
As the upcoming video coding standard, VersatileVideo coding (i.e., VVC) achieves up to 30% Bjontegaard delta bit-rate (BD-rate) reduction compared with High EfficiencyVideo coding (H.265/HEVC). To eliminate or alleviate different kinds of compression artifacts like blocking, ringing, blurring and contouring effects, three in-loop filters, i.e. de-blocking filter (DBF), sample adaptive offset (SAO) and adaptive loop filter (ALF), have been involved in VVC. Recently, Convolutional Neural Network (CNN) has attracted tremendous attention and shows great potential in many tasks in image processing. In this work, we design a CNN-based in-loop filter as an integrated single-model solution which is adaptive to almost any scenarios in video coding. An architecture named as ADCNN (i.e., Attention based Dual-scale CNN) with an attention based processing block is proposed to reduce artifacts of I frames and B frames, which take advantage of informative priors such as the quantization parameter (QP) and partitioning information. Different from existing CNN-based filtering methods, which are mainly designed for the luma component and may need to train different models for different QPs, the proposed filter is adapted to different QPs and different frame types, and all the components (i.e., both luma and chroma) are processed simultaneously with feature exchange and fusion between components for information supplementary. Experimental results show that the proposed ADCNN filter can achieve 6.54%, 13.27%, 15.72% BD-rate savings for Y, U, V respectively under the all intra configuration and 2.81%, 7.86%, 8.60% BD-rate savings under the random access configuration. It can be used to replace all the conventional in-loop filters and also outperforms them without increase in encoding time.
In this work, we carry out a study on the performance of potential JPEG's competitors when applied to document images. Many novel codecs, such as BPG, Mozjpeg, WebP and JPEG-XR, have been recently introduced in or...
详细信息
ISBN:
(纸本)9781479986385
In this work, we carry out a study on the performance of potential JPEG's competitors when applied to document images. Many novel codecs, such as BPG, Mozjpeg, WebP and JPEG-XR, have been recently introduced in order to substitute the standard JPEG. Nonetheless, there is a lack of performance evaluation of these codecs, especially for a particular category of document images. Therefore, this work makes an attempt to provide a detailed and thorough analysis of the aforementioned JPEG's competitors. To this aim, we first provide a review of the most famous codecs that have been considered as being JPEG replacements. Next, comparative experiments are performed to study the behavior of these coding schemes. Finally, we extract main remarks and conclusions characterizing the performance of these codecs for different contexts in accordance with OCR accuracy and PSNR metric.
暂无评论