Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301758
Yudong Zhou, Ronggang Wang, Yangshen Zhao
Low light Enhancement has been a hot topic in recent years, and many deep neural network (DNN)-based methods have achieved remarkable performance. However, the rapid development of DNNs also raises the urgent requirement of high-quality training sets, especially supervised night-time data sets. In this paper, we establish a night-time outdoor data set (NOD 1) that contains 1214 groups of images. We also generate appropriate and high-quality reference images for each group based on multi-exposure fusion strategy, which not only focuses on dark areas but also provides details for over-exposed areas in low light images. Furthermore, a simple but efficient network is presented as the baseline of NOD. Experimental results on NOD and other data sets show the generalizability and effectiveness of the proposed data set and baseline model.
{"title":"A night-time outdoor data set for low-light enhancement","authors":"Yudong Zhou, Ronggang Wang, Yangshen Zhao","doi":"10.1109/VCIP49819.2020.9301758","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301758","url":null,"abstract":"Low light Enhancement has been a hot topic in recent years, and many deep neural network (DNN)-based methods have achieved remarkable performance. However, the rapid development of DNNs also raises the urgent requirement of high-quality training sets, especially supervised night-time data sets. In this paper, we establish a night-time outdoor data set (NOD 1) that contains 1214 groups of images. We also generate appropriate and high-quality reference images for each group based on multi-exposure fusion strategy, which not only focuses on dark areas but also provides details for over-exposed areas in low light images. Furthermore, a simple but efficient network is presented as the baseline of NOD. Experimental results on NOD and other data sets show the generalizability and effectiveness of the proposed data set and baseline model.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132225923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301768
Chuang Ma, Ge Li, Qi Zhang, Yiting Shao, Jing Wang, Shan Liu
Due to the emerging requirement of point cloud applications, efficient point cloud compression methods are in high demand for compact point cloud representation in limited bandwidth transmission. The compression standard GPCC (Geometry-based Point Cloud Compression) is led by the MPEG (Moving Picture Expert Group) in respond to industrial requirements. KNN (K-Nearest Neighbors) search based prediction method is adopted for point cloud attribute compression in current G-PCC, which only exploits Euclidean distance-based geometric relationship without fully consideration of underlying geometric distribution. In this paper, we propose a novel prediction scheme based on fast recolor technique for attribute lossless and near-lossless compression. Our method has been implemented upon G-PCC reference software of the latest version. Experimental results show that our method can take advantage of the correlation between the attributes of neighbors, which leads to better rate-distortion (R-D) performance than G-PCC anchor on point cloud dataset with negligible encode and decode time increase under the common test conditions.
{"title":"Fast Recolor Prediction Scheme in Point Cloud Attribute Compression","authors":"Chuang Ma, Ge Li, Qi Zhang, Yiting Shao, Jing Wang, Shan Liu","doi":"10.1109/VCIP49819.2020.9301768","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301768","url":null,"abstract":"Due to the emerging requirement of point cloud applications, efficient point cloud compression methods are in high demand for compact point cloud representation in limited bandwidth transmission. The compression standard GPCC (Geometry-based Point Cloud Compression) is led by the MPEG (Moving Picture Expert Group) in respond to industrial requirements. KNN (K-Nearest Neighbors) search based prediction method is adopted for point cloud attribute compression in current G-PCC, which only exploits Euclidean distance-based geometric relationship without fully consideration of underlying geometric distribution. In this paper, we propose a novel prediction scheme based on fast recolor technique for attribute lossless and near-lossless compression. Our method has been implemented upon G-PCC reference software of the latest version. Experimental results show that our method can take advantage of the correlation between the attributes of neighbors, which leads to better rate-distortion (R-D) performance than G-PCC anchor on point cloud dataset with negligible encode and decode time increase under the common test conditions.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132868047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301820
M. Wien, B. Bross
The tutorial provides an overview on the latest emerging video coding standard VVC (Versatile Video Coding) to be jointly published by ITU-T and ISO/IEC. It has been developed by the Joint Video Experts Team (JVET), consisting of ITU-T Study Group 16 Question 6 (known as VCEG) and ISO/IEC JTC 1/SC 29/WG 11 (known as MPEG). VVC has been designed to achieve significantly improved compression capability compared to previous standards such as HEVC, and at the same time to be highly versatile for effective use in a broadened range of applications. Some key application areas for the use of VVC particularly include ultra-high-definition video (e.g. 4K or 8K resolution), video with a high dynamic range and wide colour gamut (e.g., with transfer characteristics specified in Rec. ITU-R BT.2100), and video for immersive media applications such as 360° omnidirectional video, in addition to the applications that have commonly been addressed by prior video coding standards. Important design criteria for VVC have been low computational complexity on the decoder side and friendliness for parallelization on various algorithmic levels. VVC is planned to be finalized by July 2020 and is expected to enter the market very soon.The tutorial details the video layer coding tools specified in VVC and develops the concepts behind the selected design choices. While many tools or variants thereof have been available before, the VVC design reveals many improvements compared to previous standards which result in compression gain and implementation friendliness. Furthermore, new tools such as the Adaptive Loop Filter, or Matrix-based Intra Prediction have been adopted which contribute significantly to the overall performance. The high-level syntax of VVC has been re-designed compared to previous standards such as HEVC, in order to enable dynamic sub-picture access as well as major scalability features already in version 1 of the specification.
{"title":"Versatile Video Coding – Algorithms and Specification","authors":"M. Wien, B. Bross","doi":"10.1109/VCIP49819.2020.9301820","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301820","url":null,"abstract":"The tutorial provides an overview on the latest emerging video coding standard VVC (Versatile Video Coding) to be jointly published by ITU-T and ISO/IEC. It has been developed by the Joint Video Experts Team (JVET), consisting of ITU-T Study Group 16 Question 6 (known as VCEG) and ISO/IEC JTC 1/SC 29/WG 11 (known as MPEG). VVC has been designed to achieve significantly improved compression capability compared to previous standards such as HEVC, and at the same time to be highly versatile for effective use in a broadened range of applications. Some key application areas for the use of VVC particularly include ultra-high-definition video (e.g. 4K or 8K resolution), video with a high dynamic range and wide colour gamut (e.g., with transfer characteristics specified in Rec. ITU-R BT.2100), and video for immersive media applications such as 360° omnidirectional video, in addition to the applications that have commonly been addressed by prior video coding standards. Important design criteria for VVC have been low computational complexity on the decoder side and friendliness for parallelization on various algorithmic levels. VVC is planned to be finalized by July 2020 and is expected to enter the market very soon.The tutorial details the video layer coding tools specified in VVC and develops the concepts behind the selected design choices. While many tools or variants thereof have been available before, the VVC design reveals many improvements compared to previous standards which result in compression gain and implementation friendliness. Furthermore, new tools such as the Adaptive Loop Filter, or Matrix-based Intra Prediction have been adopted which contribute significantly to the overall performance. The high-level syntax of VVC has been re-designed compared to previous standards such as HEVC, in order to enable dynamic sub-picture access as well as major scalability features already in version 1 of the specification.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133147067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301757
Jiapeng Tang, Yu Dong, Rong Xie, Xiao Gu, Li Song, Lin Li, Bing Zhou
As short video industry grows up, quality assessment of user generated videos has become a hot issue. Existing no reference video quality assessment methods are not suitable for this type of application scenario since they are aimed at synthetic videos. In this paper, we propose a novel deep blind quality assessment model for user generated videos according to content variety and temporal memory effect. Content-aware features of frames are extracted through deep neural network, and a patch-based method is adopted to obtain frame quality score. Moreover, we propose a temporal memory-based pooling model considering temporal memory effect to predict video quality. Experimental results conducted on KoNViD-1k and LIVE-VQC databases demonstrate that the performance of our proposed method outperforms other state-of-the-art ones, and the comparative analysis proves the efficiency o f our temporal pooling model.
{"title":"Deep Blind Video Quality Assessment for User Generated Videos","authors":"Jiapeng Tang, Yu Dong, Rong Xie, Xiao Gu, Li Song, Lin Li, Bing Zhou","doi":"10.1109/VCIP49819.2020.9301757","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301757","url":null,"abstract":"As short video industry grows up, quality assessment of user generated videos has become a hot issue. Existing no reference video quality assessment methods are not suitable for this type of application scenario since they are aimed at synthetic videos. In this paper, we propose a novel deep blind quality assessment model for user generated videos according to content variety and temporal memory effect. Content-aware features of frames are extracted through deep neural network, and a patch-based method is adopted to obtain frame quality score. Moreover, we propose a temporal memory-based pooling model considering temporal memory effect to predict video quality. Experimental results conducted on KoNViD-1k and LIVE-VQC databases demonstrate that the performance of our proposed method outperforms other state-of-the-art ones, and the comparative analysis proves the efficiency o f our temporal pooling model.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131641736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301772
Yuyuan Chen, Songlin Sun, Jiaqi Zhang, Shanshe Wang
AVS3 is the newest video coding standard developed by AVS (Audio Video coding Standard) group. AVS3 adopted QTBT(Quad-tree and Binary-tree) plus EQT(Extended quad-tree) block partition scheme, which makes the split process more flexible. The CU split structure is determined by a brute-force rate-distortion optimization (RDO) search. After the whole RDO search, the CU partition with minimum RD cost is selected. The flexible block partition and thorough RDO search bring promising coding gain while extremely complicate the encoder. To reduce the computational complexity of the CU split decision process in AVS3, this paper proposed a spatial information based fast split decision algorithm. In the proposed algorithm, the predicted value of split complexity was calculated firstly according to the information of spatial neighboring blocks. Then the predicted value was used to decide whether to split current CU or not. The experimental results show that the proposed algorithm resulted in average 31.03% encoding time saving with average 0.54% BD-BR loss for Random Access (RA) configuration. The proposed algorithm can greatly reduce the computational complexity of the CU split decision process with negligible performance loss.
AVS3是由AVS (Audio video coding standard)组织开发的最新视频编码标准。AVS3采用QTBT(四叉树和二叉树)+ EQT(扩展四叉树)块分区方案，使得拆分过程更加灵活。通过暴力破解率失真优化(RDO)搜索确定CU分裂结构。经过整个RDO搜索，选择RD开销最小的CU分区。灵活的分组划分和彻底的RDO搜索在使编码器极其复杂的同时带来了可观的编码增益。为了降低AVS3中CU分割决策过程的计算复杂度，提出了一种基于空间信息的快速分割决策算法。该算法首先根据空间相邻块的信息计算分割复杂度的预测值。然后用预测值来决定是否拆分当前CU。实验结果表明，该算法在随机存取(RA)配置下平均节省31.03%的编码时间，平均损失0.54%的BD-BR。该算法可以大大降低CU拆分决策过程的计算复杂度，而性能损失可以忽略不计。
{"title":"A Progressive Fast CU Split Decision Scheme for AVS3","authors":"Yuyuan Chen, Songlin Sun, Jiaqi Zhang, Shanshe Wang","doi":"10.1109/VCIP49819.2020.9301772","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301772","url":null,"abstract":"AVS3 is the newest video coding standard developed by AVS (Audio Video coding Standard) group. AVS3 adopted QTBT(Quad-tree and Binary-tree) plus EQT(Extended quad-tree) block partition scheme, which makes the split process more flexible. The CU split structure is determined by a brute-force rate-distortion optimization (RDO) search. After the whole RDO search, the CU partition with minimum RD cost is selected. The flexible block partition and thorough RDO search bring promising coding gain while extremely complicate the encoder. To reduce the computational complexity of the CU split decision process in AVS3, this paper proposed a spatial information based fast split decision algorithm. In the proposed algorithm, the predicted value of split complexity was calculated firstly according to the information of spatial neighboring blocks. Then the predicted value was used to decide whether to split current CU or not. The experimental results show that the proposed algorithm resulted in average 31.03% encoding time saving with average 0.54% BD-BR loss for Random Access (RA) configuration. The proposed algorithm can greatly reduce the computational complexity of the CU split decision process with negligible performance loss.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114374807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301794
Tong Ouyang, Zhenzhong Chen, Shan Liu
Images and videos suffer from undesirable visual artifacts at high compression ratios, which is due to the use of the discrete cosine transform and scalar quantization in the compression. To restore the quantized coefficients via producing the quantization error, we propose a coefficients restoration convolutional neural network in the frequency domain (FD-CRNet). Taking advantage of residual learning, the proposed FD-CRNet efficiently exploits the related distribution of different frequency components. The squeeze-and-excitation block (SE block) is adopted to reduce the computational complexity and better restoration performance. Experimental results show the quantized coefficients are recovered near the lossless coefficients effectively, which outperforms the existed coefficients restoration methods. In addition, the performance of methods in the spatial domain is significantly improved by FD-CRNet with more authentic details and sharper edges when removing the compression artifacts.
{"title":"Towards Quantized DCT Coefficients Restoration for Compressed Images","authors":"Tong Ouyang, Zhenzhong Chen, Shan Liu","doi":"10.1109/VCIP49819.2020.9301794","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301794","url":null,"abstract":"Images and videos suffer from undesirable visual artifacts at high compression ratios, which is due to the use of the discrete cosine transform and scalar quantization in the compression. To restore the quantized coefficients via producing the quantization error, we propose a coefficients restoration convolutional neural network in the frequency domain (FD-CRNet). Taking advantage of residual learning, the proposed FD-CRNet efficiently exploits the related distribution of different frequency components. The squeeze-and-excitation block (SE block) is adopted to reduce the computational complexity and better restoration performance. Experimental results show the quantized coefficients are recovered near the lossless coefficients effectively, which outperforms the existed coefficients restoration methods. In addition, the performance of methods in the spatial domain is significantly improved by FD-CRNet with more authentic details and sharper edges when removing the compression artifacts.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116309654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301765
Panpan Zhang, Xiuheng Wang, Tiande Gao, Zhenfu Feng, Jie Chen
A 4-dimensional (4D) image can be viewed as a stack of volumetric images over channels of observation depth or temporal frames. This data contains rich information at the cost of high demands for storage and transmission resources due to its large volume. In this paper, we present a lossless 4D image compression algorithm by extending CCSDS-123.0-B-1 standard. Instead of separately compressing the volumetric image at each channel of 4D images, the proposed algorithm efficiently exploits redundancy across the fourth dimension of data. Experiments conducted on two types of 4D images demonstrate the effectiveness of the proposed lossless compression method.
{"title":"Extending CCSDS 123.0-B-1 for Lossless 4D Image Compression","authors":"Panpan Zhang, Xiuheng Wang, Tiande Gao, Zhenfu Feng, Jie Chen","doi":"10.1109/VCIP49819.2020.9301765","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301765","url":null,"abstract":"A 4-dimensional (4D) image can be viewed as a stack of volumetric images over channels of observation depth or temporal frames. This data contains rich information at the cost of high demands for storage and transmission resources due to its large volume. In this paper, we present a lossless 4D image compression algorithm by extending CCSDS-123.0-B-1 standard. Instead of separately compressing the volumetric image at each channel of 4D images, the proposed algorithm efficiently exploits redundancy across the fourth dimension of data. Experiments conducted on two types of 4D images demonstrate the effectiveness of the proposed lossless compression method.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123630918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traditional optical flow estimation methods mostly focus on images of the same resolution. However, there are some situations requiring optical flow between images of different resolutions, where the traditional approaches suffer from the inequality of spectrum aliasing level. In this paper, we propose a method estimating the flow fields between a clear image and a highly undersampled one. The proposed method simultaneously describes the motion and integral relationship between the images via an integral form image under the assumption of brightness and gradient consistency as well as motion smoothness. We also derive the numerical solution briefly, through which we can solve the equations easily via linearizations. Experimental results on Middlebury and MPI-Sintel datasets demonstrate that our proposed method outperforms traditional methods preprocessing images of different resolutions to be the same size, offering more accurate results.
{"title":"Optical Flow Estimation Between Images of Different Resolutions via Variational Method","authors":"Rui Zhao, Ruiqin Xiong, Shuyuan Zhu, B. Zeng, Tiejun Huang, Wen Gao","doi":"10.1109/VCIP49819.2020.9301771","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301771","url":null,"abstract":"Traditional optical flow estimation methods mostly focus on images of the same resolution. However, there are some situations requiring optical flow between images of different resolutions, where the traditional approaches suffer from the inequality of spectrum aliasing level. In this paper, we propose a method estimating the flow fields between a clear image and a highly undersampled one. The proposed method simultaneously describes the motion and integral relationship between the images via an integral form image under the assumption of brightness and gradient consistency as well as motion smoothness. We also derive the numerical solution briefly, through which we can solve the equations easily via linearizations. Experimental results on Middlebury and MPI-Sintel datasets demonstrate that our proposed method outperforms traditional methods preprocessing images of different resolutions to be the same size, offering more accurate results.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124478116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301842
Heming Sun, Lu Yu, J. Katto
Intra prediction is an essential component in the image coding. This paper gives an intra prediction framework completely based on neural network modes (NM). Each NM can be regarded as a regression from the neighboring reference blocks to the current coding block. (1) For variable block size, we utilize different network structures. For small blocks 4×4 and 8×8, fully connected networks are used, while for large blocks 16×16 and 32×32, convolutional neural networks are exploited. (2) For each prediction mode, we develop a specific pre-trained network to boost the regression accuracy. When integrating into HEVC test model, we can save 3.55%, 3.03% and 3.27% BD-rate for Y, U, V components compared with the anchor. As far as we know, this is the first work to explore a fully NM based framework for intra prediction, and we reach a better coding gain with a lower complexity compared with the previous work.
{"title":"Fully Neural Network Mode Based Intra Prediction of Variable Block Size","authors":"Heming Sun, Lu Yu, J. Katto","doi":"10.1109/VCIP49819.2020.9301842","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301842","url":null,"abstract":"Intra prediction is an essential component in the image coding. This paper gives an intra prediction framework completely based on neural network modes (NM). Each NM can be regarded as a regression from the neighboring reference blocks to the current coding block. (1) For variable block size, we utilize different network structures. For small blocks 4×4 and 8×8, fully connected networks are used, while for large blocks 16×16 and 32×32, convolutional neural networks are exploited. (2) For each prediction mode, we develop a specific pre-trained network to boost the regression accuracy. When integrating into HEVC test model, we can save 3.55%, 3.03% and 3.27% BD-rate for Y, U, V components compared with the anchor. As far as we know, this is the first work to explore a fully NM based framework for intra prediction, and we reach a better coding gain with a lower complexity compared with the previous work.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127111552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.1109/VCIP49819.2020.9301826
Kexin Chen, Xue Zhou, Chao Liang, Jianxiao Zou
This paper presents an online template update method with bidirectional consistency constraint for Siamese trackers. Due to continuously applying cross-correlation mechanism between template and the search region, the performance of Siamese trackers highly relies on the fidelity of template. Therefore, besides standard linear update, learning the template update methods attract attention. Inspired by this, in this paper we adopt a learning to update model called UpdateNet as our baseline. Different from it, we further propose a novel bi-directional consistency loss as a constraint to learn the template update more smoothly and stably. Our method considers both forward and backward information for each medium frame, thus introducing a multi-stage bidirectional simulated tracking training mechanism. We apply our model to a Siamese tracker, SiamRPN and demonstrate the effectiveness and robustness of our proposed method compared with traditional UpdateNet in the Large-scale Single Object Tracking (LaSOT) dataset.
{"title":"Bidirectional Consistency Constrained Template Update Learning for Siamese Trackers","authors":"Kexin Chen, Xue Zhou, Chao Liang, Jianxiao Zou","doi":"10.1109/VCIP49819.2020.9301826","DOIUrl":"https://doi.org/10.1109/VCIP49819.2020.9301826","url":null,"abstract":"This paper presents an online template update method with bidirectional consistency constraint for Siamese trackers. Due to continuously applying cross-correlation mechanism between template and the search region, the performance of Siamese trackers highly relies on the fidelity of template. Therefore, besides standard linear update, learning the template update methods attract attention. Inspired by this, in this paper we adopt a learning to update model called UpdateNet as our baseline. Different from it, we further propose a novel bi-directional consistency loss as a constraint to learn the template update more smoothly and stably. Our method considers both forward and backward information for each medium frame, thus introducing a multi-stage bidirectional simulated tracking training mechanism. We apply our model to a Siamese tracker, SiamRPN and demonstrate the effectiveness and robustness of our proposed method compared with traditional UpdateNet in the Large-scale Single Object Tracking (LaSOT) dataset.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129950288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：