浏览全部资源
扫码关注微信
网络出版日期： 2025-02-17 ，
录用日期： 2025-02-13
移动端阅览
丁晓颖,张新峰,Lin Weisi等.三维模型视觉显著性检测研究综述[J].中国图象图形学报,
Ding Xiaoying,Zhang Xinfeng,Lin Weisi,et al.Review of visual saliency detection for 3D object models[J].Journal of Image and Graphics,
三维模型视觉显著性检测通过模拟人类视觉系统，定位模型中蕴含重要视觉信息的区域，被广泛应用于模型简化、分割、压缩等相关任务，是计算机视觉领域的热点研究问题。区别于图像和视频数据，三维模型体量庞大、数据分布并不均匀，同时噪声数据较多，使得现有图像和视频视觉显著性检测方法难以被拓展应用，为三维模型视觉显著性检测任务带来了巨大的挑战。针对这一现状，本文首先对近年来国内外公开发表的三维模型视觉显著性检测方法进行概述，根据使用特征的不同将三维模型视觉显著性检测方法分为基于手工特征的方法和基于深度学习的方法，并根据不同三维模型表示形式分别介绍面向点云模型的方法和面向网格模型的方法。对基于手工特征的方法，根据特征尺度的不同将其细分为基于单尺度特征的方法和基于多尺度特征的方法，重点介绍特征提取策略；对基于深度学习的方法，重点介绍设计思路。同时，本文对现有三维模型视觉显著性检测数据集进行汇总，介绍三维模型视觉显著性检测常用的性能评价指标，并对部分方法进行性能对比。此外，本文详细介绍视觉显著性检测结果在三维模型缩放、简化、降噪以及质量评价等相关领域的应用。最后，基于国内外研究现状，本文讨论三维模型视觉显著性检测领域亟需解决的问题，并指出未来可能的发展方向。
With the fast development of point cloud acquisition technology and the popularity of portable point cloud acquisition equipment， generating 3D model with high density and rich texture information is much easier than ever before. Three-dimensional （3D） model can represent the real world with rich information and has been widely applied in various applications in our daily life， such as smart cities， autonomous driving， virtual reality and product design， making 3D model processing a hot research topic in the fields related to computer vision and 3D graphics. However， the growing number and size of 3D models bring great challenges to storage， transmission and processing. Facing this huge amount of data， directly processing the whole 3D model in real time is impractical or uneconomical in many situations. Inspired by the selective mechanism of the human visual system （HVS）， which indicates that the HVS selectively processes the huge amount of visual information that comes into our eyes and distributes more of the limited attention to regions with important visual information， researchers begin to investigate whether this selective mechanism can be applied to deal with 3D models. In essence， 3D visual saliency detection aims to detect the visually salient regions on 3D models and can help with various human-centered applications in 3D model processing， e.g.， resizing， simplification， segmentation and quality assessment. Different from 2D image and video data which have regular pixel distribution， a 3D model contains depth information， noise data and is usually with larger data size. More often than not， points are distributed unevenly in 3D space， making it hard to extend existing image and video visual saliency detection methods to deal with 3D models straightforwardly. Besides， unlike 2D image and video visual saliency detection which have been studied by researchers for decades， research towards 3D visual saliency detection has just started during recent years. Considering the fact that humans are the final users for most small 3D object while machines are final users for large-scale/city-scale scenarios， in this paper， we summarize studies related to visual saliency detection for 3D object models to provide a comprehensive survey. Firstly， we summarize existing 3D visual saliency detection methods. Considering the different kind of features used by researchers， these 3D visual saliency detection methods can be classified into two categories： hand-crafted feature based methods and deep-learning based methods. The former category can be further divided into two different types， namely， the single-scale feature based methods and the multi-scale feature based ones. Besides， according to different 3D representations， these methods can also be divided into 3D point-cloud based methods and 3D mesh based ones. We will also investigate their feature extraction strategies and multi-feature integration frameworks. Compared to traditional hand-crafted feature based methods， deep-learning based methods achieve higher similarity with the ground-truth human labeling and fixation density maps. This is because deep-learning based features usually have stronger expressive power when compared to hand-crafted features. Then， we summarize 3D visual saliency detection databases which can be used to achieve and evaluate the performance of different 3D visual saliency detection methods. Based on different data collection approaches， these databases can be categorized into two different classes： mouse-tracking based database and eye-tracking based database. Limited by the eye-tracking technology， earlier 3D visual saliency detection databases were mainly constructed using mouse-tracking technology. Compared to eye-tracking， mouse-tracking is cheaper and easier to be implemented. With development of eye-tracking technology in recent years， researchers tend to use eye-tracking technology to construct 3D visual saliency detection database since it is more straightforward to record the human visual behavior. During the eye-tracking experiment， several subjects will be invited to freely observe 3D models or their projected images without any specific task. Their eye-movement data will be collected during this observation and subsequently processed to construct the database. Moreover， we also provide clear illustrations about the commonly used evaluation metrics for evaluating the performance of 3D visual saliency detection methods， such as the correlation coefficient （CC） score and the AUC score. In addition， we introduce how 3D visual saliency detection can be used as a guidance to improve the visual performance of other 3D model processing applications including 3D model resizing， simplification， denoising and quality assessment. In 3D model resizing， uniformly adjusting the size of the entire 3D model may lead to unsatisfying visual performance since it could potentially cause excessive stretching of certain areas on the 3D model and will lead to visual distortions， introducing visual saliency information can better preserve the structural features of the 3D model. In 3D model simplification， 3D visual saliency detection result identifies regions that are visually salient， which can guide the simplification procedure to preserve more details in visually salient regions and lead to more visual appealing results. In 3D model denoising， visual saliency feature can help determine parameters of the denoising filter， allowing for better preservation of detailed features in the denoised 3D model. In 3D model quality assessment， distortions in visually salient regions are more annoying than distortions appeared in unsalient regions. Thus， accurately detecting visually salient regions on 3D model is of vital importance to 3D quality assessment and can help to obtain a more precise quality evaluation results. Finally， we provide an in-depth conclusion about 3D model visual saliency detection and discuss the problems that need to be solved. Moreover， we introduce the development trends of 3D model visual saliency detection from two perspectives： content of the 3D model and design of the algorithm， hoping it can help with further improvement and trigger further exploration in the research community.
Abid M ， Da Silva M P ， Le Callet P . 2020 . Towards visual saliency computation on 3D graphical contents for interactive visualization // IEEE International Conference on Image Processing . Abu Dhabi， UAE ： IEEE： 3448 - 3452 ［ DOI： 10.1109/ICIP40778.2020.9191064 http://dx.doi.org/10.1109/ICIP40778.2020.9191064 ］
Abouelaziz I ， Chetouani A ， Hassouni M E ， Latecki L J and Cherifi H . 2020 . 3D visual saliency and convolutional neural network for blind mesh quality assessment . Neural Computing and Applications ， 32 ： 16589 - 16603 ［ DOI： 10.1007/s00521-019-04521-1 http://dx.doi.org/10.1007/s00521-019-04521-1 ］
Achanta R ， Shaji A ， Smith K ， Lucchi A ， Fua P and Süsstrunk S . 2012 . SLIC superpixels compared to state-of-the-art superpixel methods . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 34 （ 11 ）： 2274 - 2282 ［ DOI： 10.1109/TPAMI.2012.120 http://dx.doi.org/10.1109/TPAMI.2012.120 ］
Alexiou E ， Xu P and Ebrahimi T . 2019 . Towards modelling of visual saliency in point clouds for immersive applications // IEEE International Conference on Image Processing . Taipei， China ： IEEE： 4325 - 4329 ［ DOI： 10.1109/ICIP.2019.8803479 http://dx.doi.org/10.1109/ICIP.2019.8803479 ］
Alfarasani D A ， Sweetman T ， Lai Y K and Rosin P L . 2022 . Learning to predict 3D mesh saliency // International Conference on Pattern Recognition ， Montreal， Canada ： IEEE： 4023 - 4029 ［ DOI： 10.1109/ICPR56361.2022.9956579 http://dx.doi.org/10.1109/ICPR56361.2022.9956579 ］
An G ， Watanabe T and Kakimoto M . 2016 . Mesh simplification using hybrid saliency // IEEE International Conference on Cyberworlds . Chongqing， China ： IEEE： 231 - 234 ［ DOI： 10.1109/CW.2016.47 http://dx.doi.org/10.1109/CW.2016.47 ］
An P ， Duan Y C ， Huang Y L ， Ma J ， Chen Y F ， Wang L H ， Yang Y ， and Liu Q . 2023 . SP-Det： leveraging saliency prediction for voxel-based 3D object detection in sparse point cloud . IEEE Transactions on Multimedia ， 26 ： 2795 - 2808 ［ DOI： 10.1109/TMM.2023.3304054 http://dx.doi.org/10.1109/TMM.2023.3304054 ］
Anjos R K D ， Roberts R A ， Allen B ， Jorge J and Anjyo K . 2023 . Saliency detection for large-scale mesh decimation. Computers and Graphics， 111 （C） ： 63 - 76 ［ DOI： 10.1016/j.cag.2023.01.012 http://dx.doi.org/10.1016/j.cag.2023.01.012 ］
Armeni I ， Sax S ， Zamir A R and Savarese S . 2017 . Joint 2D-3D-semantic data for indoor scene understanding ［2017-04-06］ . https：//arxiv.org/pdf/1702.01105.pdf https://arxiv.org/pdf/1702.01105.pdf
Arvanitis G ， Lalos A S and Moustakas K . 2021 . Robust and fast 3D saliency mapping for industrial modeling applications . IEEE Transactions on Industrial Informatics ， 17 （ 2 ）： 1307 - 1317 ［ DOI： 10.1109/TII.2020.3003455 http://dx.doi.org/10.1109/TII.2020.3003455 ］
Aspert N ， Santa-Cruz D and Ebrahimi T . 2002 . Mesh： measuring errors between surfaces using the Hausdorff distance // IEEE International Conference on Multimedia and Expo . Lausanne， Switzerland ： IEEE： 705 - 708 ［ DOI： 10.1109/ICME.2002.1035879 http://dx.doi.org/10.1109/ICME.2002.1035879 ］
Chen C L Z ， Wang G T ， Peng C ， Zhang X W and Qin H . 2019 . Improved robust video saliency detection based on long-term spatial-temporal information ， IEEE Transactions on Image Processing ， 29 ： 1090 - 1100 ［ DOI： 10.1109/TIP.2019.2934350 http://dx.doi.org/10.1109/TIP.2019.2934350 ］
Chen G ， Dai H ， Zhou T ， Shen J and Shao L . 2023 . Automatic schelling point detection from meshes . IEEE Transactions on Visualization and Computer Graphics ， 29 （ 6 ）： 2926 - 2939 ［ DOI： 10.1109/TVCG.2022.3144143 http://dx.doi.org/10.1109/TVCG.2022.3144143 ］
Chen X B ， Saparov A ， Pang B and Funkhouser T . 2012 . Schelling points on 3D surface meshes . ACM Transactions on Graphics ， 31 （ 4 ）： 1 - 12 ［ DOI： 10.1145/2185520.2185525 http://dx.doi.org/10.1145/2185520.2185525 ］
Cignoni P ， Rocchini C and Scopigno R . 1998 . Metro： measuring error onsimplified surfaces . Computer Graphics Forum ， 17 （ 2 ）： 167 - 174 ［ DOI： 10.1111/1467-8659.00236 http://dx.doi.org/10.1111/1467-8659.00236 ］
Ding G Q ， Imamoglu N ， Caglayan A ， Murakawa M and Nakamura R . 2022a . SalLiDAR： saliency knowledge transfer learning for 3D point cloud understanding // British Machine Vision Conference ， London， UK ： BMVA： 1 - 14
Ding G Q ， Imamoglu N ， Caglayan A ， Murakawa M and Nakamura R . 2024a . Attention-guided LiDAR segmentation and odometry using image-to-point cloud saliency transfer . Multimedia Systems ， 30 ： 188 ［ DOI： 10.1007/s00530-024-01389-7 http://dx.doi.org/10.1007/s00530-024-01389-7 ］
Ding X Y ， Lin W S ， Chen Z Z and Zhang X F . 2019 . Point cloud saliency detection by local and global feature fusion . IEEE Transactions on Image Processing ， 28 （ 11 ）： 5379 - 5393 ［ DOI： 10.1109/TIP.2019.2918735 http://dx.doi.org/10.1109/TIP.2019.2918735 ］
Ding X Y and Chen Z Z . 2022b . Towards mesh saliency in 6 degrees of freedom . Neurocomputing ， 502 ： 120 - 139 ［ DOI： 10.1016/j.neucom.2022.06.088 http://dx.doi.org/10.1016/j.neucom.2022.06.088 ］
Ding X Y ， Chen Z ， Lin W S and Chen Z Z . 2024b . Towards 3D colored mesh saliency： database and benchmarks . IEEE Transactions on Multimedia ， 26 ： 3580 - 3591 ［ DOI： 10.1109/TMM.2023.3312924 http://dx.doi.org/10.1109/TMM.2023.3312924 ］
Dutagaci H ， Cheung C P and Godil A . 2012 . Evaluation of 3D interest point detection techniques via human-generated ground truth . The Visual Computer ， 28 ： 901 - 917 ［ DOI： 10.1007/s00371-012-0746-4 http://dx.doi.org/10.1007/s00371-012-0746-4 ］
Dutta S ， Banerjee S ， Biswas P K and Bhowmick P . 2014 . Mesh denoising using multi-scale curvature-based saliency // Asian Conference on Computer Vision Workshops . Singapore， Singapore ： Springer： 507 - 516 ［ DOI： 10.1007/978-3-319-16631-5_37 http://dx.doi.org/10.1007/978-3-319-16631-5_37 ］
Elad M . 2005 . Retinex by two bilateral filters // International Conference on Scale-Space Theories in Computer Vision . Berlin， Germany ： Springer： 217 - 229 ［ DOI： 10.1007/11408031_19 http://dx.doi.org/10.1007/11408031_19 ］
Feng X ， Wan W G ， Xu R Y D ， Perry S ， Zhu S and Liu Z . 2018 . A new mesh visual quality metric using saliency weighting-based pooling strategy . Graphical Models ， 99 ： 1 - 12 ［ DOI： 10.1016/j.gmod.2018.07.001 http://dx.doi.org/10.1016/j.gmod.2018.07.001 ］
Figueiredo V F ， Sandri G L ， de Queiroz R L and Chou P A . 2020 . Saliency maps for point clouds // IEEE International Workshop on Multimedia Signal Processing ， Tampere， Finland ： IEEE： 1 - 5 ［ DOI： 10.1109/MMSP48831.2020.9287102 http://dx.doi.org/10.1109/MMSP48831.2020.9287102 ］
Fleishman S ， Drori I ， Cohen-or D . 2003 . Bilateral mesh denosing . ACM Transactions on Graphics ， 22 ： 950 - 953 ［ DOI： 10.1145/882262.88236 http://dx.doi.org/10.1145/882262.88236 ］
Garland M and Heckbert P S . 1997 . Surface simplification using quadric error metrics // Annual Conference on Computer Graphics and Interactive Techniques . Los Angeles， USA ： ACM： 209 - 216 ［ DOI： 10.1145/258734.258849 http://dx.doi.org/10.1145/258734.258849 ］
Garland M and Heckbert P S . 1998 . Simplifying surfaces with color and texture using quadric error metrics // Proceedings of Visualization . Research Triangle Park， USA ： IEEE： 263 - 269 ［ DOI： 10.1109/VISUAL.1998.745312 http://dx.doi.org/10.1109/VISUAL.1998.745312 ］
Guo Y ， Wang F and Xin J M . 2017 . Point-wise saliency detection on 3D point clouds via covariance descriptors . The Visual Computer ， 34 ： 1325 - 1338 ［ DOI： 10.1007/s00371-017-1416-3 http://dx.doi.org/10.1007/s00371-017-1416-3 ］
Hou T B ， Qin H . 2013 . Admissible diffusion wavelets and their applications in space-frequency processing . IEEE Transactions on Visualization and Computer Graphics ， 19 （ 1 ）： 3 - 15 ［ DOI： 10.1109/TVCG.2012.111 http://dx.doi.org/10.1109/TVCG.2012.111 ］
Howlett S ， Hamill J and O'Sullivan C . 2005 . Predicting and evaluating saliency for simplified polygonal models . ACM Transactions on Applied Perception ， 2 （ 3 ）： 286 - 308 ［ DOI： 10.1145/1077399.1077406 http://dx.doi.org/10.1145/1077399.1077406 ］
Hu S F ， Liang X H ， Shum H P H ， Li F W B and Aslam N . 2020a . Sparse metric-based mesh saliency . Neurocomputing ， 400 ： 11 - 23 ［ DOI： 10.1016/j.neucom.2020.02.106 http://dx.doi.org/10.1016/j.neucom.2020.02.106 ］
Hu S F ， Shum H P H ， Aslam N ， Li F W B and Liang X H . 2020b . A unified deep metric representation for mesh saliency detection and non-rigid shape matching . IEEE Transactions on Multimedia ， 22 （ 9 ）： 2278 - 2292 ［ DOI： 10.1109/TMM.2019.2952983 http://dx.doi.org/10.1109/TMM.2019.2952983 ］
Jeong S W ， Yun J S and Sim J Y . 2020 . Multi-scale saliency detection for colored 3D point clouds based on random walk // Asia-Pacific Signal and Information Processing Association Annual Summit and Conference ， Auckland， New Zealand ： IEEE： 1193 - 1200
Jia S X ， Zhang C M ， Li X M and Zhou Y F . 2014 . Mesh resizing based on hierarchical saliency detection . Graphical Models ， 76 （ 5 ）： 355 - 362 ［ DOI： 10.1016/j.gmod.2014.03.012 http://dx.doi.org/10.1016/j.gmod.2014.03.012 ］
Jiang M ， Huang S S ， Duan J Y and Zhao Q . 2015 . SALICON： saliency in context // IEEE Conference on Computer Vision and Pattern Recognition . Boston， USA ： IEEE： 1072 - 1080 ［ DOI： 10.1109/CVPR.2015.7298710 http://dx.doi.org/10.1109/CVPR.2015.7298710 ］
Jiang Z Y ， Ding L Y ， Tam G K L ， Song C ， Li F W B and Yang B L . 2023 . C2SPoint： A classification-to-saliency network for point cloud saliency detection . Computers & Graphics ， 115 ： 274 - 284 ［ DOI： 10.1016/j.cag.2023.07.003 http://dx.doi.org/10.1016/j.cag.2023.07.003 ］
Kim Y ， Varshney A ， Jacobs D W and Guimbretière F . 2010 . Mesh saliency and human eye fixations . ACM Transactions on Applied Perception ， 7 （ 2 ）： 1 - 13 ［ DOI： 10.1145/1670671.1670676 http://dx.doi.org/10.1145/1670671.1670676 ］
Kraevoy V ， Sheffer A ， Shamir A and Cohen-Or D . 2008 . Non-homogeneous resizing of complex models . ACM Transactions on Graphics ， 27 （ 5 ）： 1 - 9 ［ DOI： 10.1145/1409060.1409064 http://dx.doi.org/10.1145/1409060.1409064 ］
Lavoué G ， Cordier F ， Seo H and Larabi M . 2018 . Visual attention for rendered 3D shapes . Computer Graphics Forum ， 37 （ 2 ）： 191 - 203 ［ DOI： 10.1111/cgf.13353 http://dx.doi.org/10.1111/cgf.13353 ］
Leal E ， Sanchez-Torres G ， Branch-Bedoya J W ， Abad F and Leal N . 2021 . A saliency-based sparse representation method for point cloud simplification . Sensors ， 21 （ 13 ）： 4279 - 4297 ［ DOI： 10.3390/s21134279 http://dx.doi.org/10.3390/s21134279 ］
Lee C H ， Varshney A and Jacobs D W . 2005 . Mesh saliency . ACM Transactions on Graphics ， 24 （ 3 ）： 659 - 666 ［ DOI： 10.1145/1073204.1073244 http://dx.doi.org/10.1145/1073204.1073244 ］
Leifman G ， Shtrom E and Tal A . 2016 . Surface regions of interest for viewpoint selection . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 38 （ 12 ）： 2544 - 2556 ［ DOI： 10.1109/TPAMI.2016.2522437 http://dx.doi.org/10.1109/TPAMI.2016.2522437 ］
Li B ， Yang Y and Liu Q . 2021 . RGB-D video saliency detection via superpixel-level conditional random field . Journal of Image and Graphics ， 26 （ 4 ）： 872 - 882 .
李贝 ， 杨铀 ， 刘琼 . 2021 . 超像素条件随机场下的RGB-D视频显著性检测 . 中国图象图形学报 ， 26 （ 4 ）： 872 - 882 ［ DOI： 10.11834/jig.200122 http://dx.doi.org/10.11834/jig.200122 ］
Li H ， Ye W C ， Zhang G F ， Zhang S Y and Bao H J . 2020 . Saliency guided subdivision for single-view mesh reconstruction // International Conference on 3D Vision ， Fukuoka， Japan ： IEEE： 1098 - 1107 ［ DOI： 10.1109/3DV50981.2020.00120 http://dx.doi.org/10.1109/3DV50981.2020.00120 ］
Li T ， Liu W ， Liu H ， Wang J and Liu L G . 2019 . Feature-convinced mesh denoising . Graphical Models ， 101 ： 17 - 26 ［ DOI： 10.1016/j.gmod.2018.12.002 http://dx.doi.org/10.1016/j.gmod.2018.12.002 ］
Lin T Y ， Maire M ， Belongie S ， Hays J ， Perona P ， Ramanan D ， Dollár P and Zitnick C L . 2014 . Microsoft COCO： common objects in context // European Conference on Computer Vision . Zurich， Switzerland ： Springer： 740 - 755 ［ DOI： 10.1007/978-3-319-10602-1_48 http://dx.doi.org/10.1007/978-3-319-10602-1_48 ］
Lin W S and Lee S H . 2022 . Visual saliency and quality evaluation for 3D point clouds and meshes： an overview . APSIPA Transactions on Signal and Information Processing ， 11 （ 1 ）： 1 - 50 ［ DOI： 10.1561/116.00000125 http://dx.doi.org/10.1561/116.00000125 ］
Linardos A ， Kümmerer M ， Press O and Bethge M . 2021 . DeepGaze IIE： calibrated prediction in and out-of-domain for state-of-the-art saliency modeling // IEEE International Conference on Computer Vision ， Montreal， Canada ： IEEE： 12899 - 12908 ［ DOI： 10.1109/ICCV48922.2021.01268 http://dx.doi.org/10.1109/ICCV48922.2021.01268 ］
Liu C M ， Luan W N ， Fu R H and Pang H B . 2023， Attention-embedding mesh saliency . The Visual Computer ， 39 ： 1783 - 1795 ［ DOI： 10.1007/s00371-022-02444-y http://dx.doi.org/10.1007/s00371-022-02444-y ］
Liu X P ， Tao P P ， Cao J J ， Chen H and Zou C Q . 2016a . Mesh saliency detection via double absorbing Markov chain in feature space . The Visual Computer ， 32 ： 1121 - 1132 ［ DOI： 10.1007/s00371-015-1184-x http://dx.doi.org/10.1007/s00371-015-1184-x ］
Liu X Y ， Liu L G ， Song W J ， Liu Y P and Ma L Z . 2016b . Shape context based mesh saliency detection and its applications： a survey. Computers and Graphics， 57 （c） ： 12 - 30 ［ DOI： 10.1016/j.cag.2016.03.001 http://dx.doi.org/10.1016/j.cag.2016.03.001 ］
Liu X Y ， Yan M Y and Bohg J . 2019 . MeteorNet： deep learning on dynamic 3D point cloud sequences // IEEE International Conference on Computer Vision ， Seoul， Korea ： IEEE： 9245 - 9254 ［ DOI： 10.1109/ICCV.2019.00934 http://dx.doi.org/10.1109/ICCV.2019.00934 ］
Luan W N ， Liu C M and Pang H B . 2020 . Skeleton-bridged mesh saliency and mesh simplification // International Conference on Computer Science and Artificial Intelligence ， Zhuhai， China ： ACM： 278 - 283 ［ DOI： 10.1145/3445815.344586 http://dx.doi.org/10.1145/3445815.344586 ］
Martin D ， Fandos A ， Masia B and Serrano A . 2023 . SAL3D： a model for saliency prediction in 3D meshes . The Visual Computer ， 40 ： 7761 - 7771 ［10.1007/s00371-023-03206-0］
Maximo A ， Patro R ， Varshney A and Farias R . 2011 . A robust and rotationally invariant local surface descriptor with applications to non-local mesh processing . Graphical Models ， 73 （ 5 ）： 231 - 242 ［ DOI： 10.1016/j.gmod.2011.05.002 http://dx.doi.org/10.1016/j.gmod.2011.05.002 ］
Miao Y W and Lin H B . 2013 . Visual saliency guided global and local resizing for 3D models // International Conference on Computer-Aided Design and Computer Graphics ， Guangzhou， China ： IEEE： 212 - 219 ［ DOI： 10.1109/CADGraphics.2013.35 http://dx.doi.org/10.1109/CADGraphics.2013.35 ］
Nehmé Y ， Abid M ， Lavoué G ， Da Silva M P and Le Callet P . 2021 . Cmdm-Vac： improving a perceptual quality metric for 3D graphics by integrating a visual attention complexity measure // IEEE International Conference on Image Processing ， Anchorage， USA ： IEEE： 3368 - 3372 ［ DOI： 10.1109/ICIP42928.2021.9506662 http://dx.doi.org/10.1109/ICIP42928.2021.9506662 ］
Nie W Z ， Qu L ， Ren M J ， Liang Q ， Su Y T ， Li Y Y and Jin H . 2020 . Two-stream network based on visual saliency sharing for 3D model recognition . IEEE Access ， 8 ： 5979 - 5989 ［ DOI： 0.1109/ACCESS.2019.2963511 http://dx.doi.org/0.1109/ACCESS.2019.2963511 ］
Nouri A ， Charrier C ， Lézoray O . 2015a . Mesh saliency with adaptive local patches // Three-Dimensional Image Processing， Measurement， and Applications ， San Francisco， USA ： SPIE： 98 - 109 ［ DOI： 10.1117/12.2076656 http://dx.doi.org/10.1117/12.2076656 ］
Nouri A ， Charrier C ， Lézoray O . 2015b . Multi-scale mesh saliency with local adaptive patches for viewpoint selection . Signal Processing： Image Communication ， 38 ： 151 - 166 ［ DOI： 10.1016/j.image.2015.08.002 http://dx.doi.org/10.1016/j.image.2015.08.002 ］
Nouri A ， Charrier C ， Lézoray O . 2015c . Multi-scale saliency of 3D colored meshes // IEEE International Conference on Image Processing ， Quebec City， Canada ： IEEE： 2820 - 2824 ［ DOI： 10.1109/ICIP.2015.7351317 http://dx.doi.org/10.1109/ICIP.2015.7351317 ］
Nouri A ， Charrier C ， Lézoray O . 2016 . Full-reference saliency-based 3D mesh quality assessment index // IEEE International Conference on Image Processing ， Phoenix， USA ： IEEE： 1007 - 1011 ［ DOI： 10.1109/ICIP.2016.7532509 http://dx.doi.org/10.1109/ICIP.2016.7532509 ］
Nouri A ， Charrier C ， Lézoray O . 2017 . Global visual saliency： Geometric and colorimetrie saliency fusion and its applications for 3D colored meshes // International Conference on Image Processing Theory， Tools and Applications ， Montreal， Canada ： IEEE： 1 - 6 ［ DOI： 10.1109/IPTA.2017.8310142 http://dx.doi.org/10.1109/IPTA.2017.8310142 ］
Nouri A ， Charrier C ， Lézoray O . 2022 . A genetically based combination of visual saliency and roughness for FR 3D mesh quality assessment： a statistical study . The Computer Journal ， 65 （ 3 ）： 606 - 620 ［ DOI： 10.1093/comjnl/bxaa089 http://dx.doi.org/10.1093/comjnl/bxaa089 ］
Nouri A ， Lézoray O ， Ibork Z ， Charrier C and Touahni R . 2024 . A fully automatic colorimetric saliency detection approach for 3D meshes // International Conference on Signal， Image， Video and Communications ， Marrakech， Morocco ： IEEE： 1 - 5 ［DOI： 10.1109/ISIVC61350.2024.10577926］.
Nousias S ， Arvanitis G ， Lalos A S and Moustakas K . 2020a . Mesh saliency detection using convolutional neural networks // IEEE International Conference on Multimedia and Expo ， London， UK ： IEEE： 1 - 6 ［ DOI： 10.1109/ICME46284.2020.9102796 http://dx.doi.org/10.1109/ICME46284.2020.9102796 ］
Nousias S ， Arvanitis G ， Lalos A S ， Pavlidis G ， Koulamas C ， Kalogeras A and Moustakas K . 2020b . A saliency aware CNN-based 3D model simplification and compression framework for remote inspection of heritage sites . IEEE Access ， 8 ： 169982 – 170001 ［ DOI： 10.1109/ACCESS.2020.3023167 http://dx.doi.org/10.1109/ACCESS.2020.3023167 ］
Nousias S ， Arvanitis G ， Lalos A S and Moustakas K . 2023 . Deep saliency mapping for 3D meshes and applications . ACM Transactions on Multimedia Computing， Communications and Applications ， 19 （ 2 ）： 1 - 22 ［ DOI： 10.1145/3550073 http://dx.doi.org/10.1145/3550073 ］
Nozawa N ， Fukusato T and Morishima S . 2017 . 3D model partial-resizing via normal and texture map combination // ACM SIGGRAPH ， Los Angeles， USA ： ACM： 1 - 2 ［DOI： 10.1145/3102163.3102203］.
Qi C R ， Su H ， Mo K C and Guibas L J . 2017a . PointNet： deep learning on point sets for 3D classification and segmentation // IEEE Conference on Computer Vision and Pattern Recognition ， Honolulu， USA ： IEEE： 77 - 85 ［ DOI： 10.1109/CVPR.2017.16 http://dx.doi.org/10.1109/CVPR.2017.16 ］
Qi C R ， Yi L ， Su H and Guibas L J . 2017b . PointNet++： deep hierarchical feature learning on point sets in a metric space // Conference on Neural Information Processing Systems ， Long Beach， USA ： MIT： 5105 - 5114 ［ DOI： 10.5555/3295222.3295263 http://dx.doi.org/10.5555/3295222.3295263 ］
Rouhafzay G ， Cretu A M and Payeur P . 2023 . A deep model of visual attention for saliency detection on 3D objects . Neural Processing Letters ， 55 ： 8847 - 8868 ［ DOI： 10.1007/s11063-023-11180-w http://dx.doi.org/10.1007/s11063-023-11180-w ］
Rusu R B ， Blodow N and Beetz M . 2009 . Fast point feature histograms （FPFH） for 3D registration // IEEE International Conference on Robotics and Automation . Kobe， Japan ： IEEE： 3212 - 3217 ［ DOI： 10.1109/ROBOT.2009.5152473 http://dx.doi.org/10.1109/ROBOT.2009.5152473 ］
Shtrom E ， Leifman G and Tal A . 2013 . Saliency detection in large point sets // IEEE International Conference on Computer Vision . Sydney， Australia ： IEEE： 3591 - 3598 ［ DOI： 10.1109/ICCV.2013.446 http://dx.doi.org/10.1109/ICCV.2013.446 ］
Song R ， Liu Y H ， Martin R R and Echavarria K R . 2016 . Local-to-global mesh saliency . The Visual Computer ， 34 ： 323 - 336 ［ DOI： 10.1007/s00371-016-1334-9 http://dx.doi.org/10.1007/s00371-016-1334-9 ］
Song R ， Liu Y H ， Martin R R and Rosin P L . 2014 . Mesh saliency via spectral processing . ACM Transactions on Graphics ， 33 （ 1 ）： 1 - 17 ［ DOI： 10.1145/2530691 http://dx.doi.org/10.1145/2530691 ］
Song R ， Liu Y H ， Zhao Y T ， Martin R R and Rosin P L . 2012 . Conditional random field-based mesh saliency // IEEE International Conference on Image Processing . Orlando， USA ： IEEE： 637 - 640 ［ DOI： 10.1109/ICIP.2012.6466940 http://dx.doi.org/10.1109/ICIP.2012.6466940 ］
Song R ， Liu Y H and Rosin P L . 2021a . Mesh saliency via weakly supervised classification-for-saliency CNN . IEEE Transactions on Visualization and Computer Graphics ， 27 （ 1 ）： 151 - 164 ［ DOI： 10.1109/TVCG.2019.2928794 http://dx.doi.org/10.1109/TVCG.2019.2928794 ］
Song R ， Zhang W ， Zhao Y T ， Liu Y H and Rosin P L . 2021b . Mesh saliency： an independent perceptual measure or a derivative of image saliency？ // IEEE Conference on Computer Vision and Pattern Recognition . Nashville， USA ： IEEE： 8853 - 8862 ［ DOI： 10.1109/CVPR46437.2021.00874 http://dx.doi.org/10.1109/CVPR46437.2021.00874 ］
Song R ， Zhang W ， Zhao Y T and Liu Y H . 2022 . Unsupervised multi-view CNN for salient view selection and 3D interest point detection . International Journal of Computer Vision ， 130 ： 1210 - 1227 ［ DOI： 10.1007/s11263-022-01592-x http://dx.doi.org/10.1007/s11263-022-01592-x ］
Song R ， Zhang W ， Zhao Y T ， Liu Y H and Rosin P L . 2023 . 3D visual saliency： an independent perceptual measure or a derivative of 2D image saliency？ IEEE Transactions on Pattern Analysis and Machine Intelligence ， 45 （ 11 ）： 13083 - 13099 ［ DOI： 10.1109/TPAMI.2023.3287356 http://dx.doi.org/10.1109/TPAMI.2023.3287356 ］
Sun J ， Ovsjanikov M and Guibas L . 2009 . A concise and provably informative multi-scale signature based on heat diffusion ， Computer Graphics Forum ， 28 （ 5 ）： 1383 - 1392 ［ DOI： 10.1111/j.1467-8659.2009.01515.x http://dx.doi.org/10.1111/j.1467-8659.2009.01515.x ］
Sun Y ， Chen C Y ， Hu X J ， Li L and Xing Q W . 2022 . Saliency detection algorithm of panoramic images using joint weighting with observer’s attention longitude . Journal of Image and Graphics ， 27 （ 4 ）： 1322 - 1334 .
孙耀 ， 陈纯毅 ， 胡小娟 ， 李凌 ， 邢琦玮 . 2022 . 观看经度联合加权全景图显著性检测算法 . 中国图象图形学报 ， 27 （ 4 ）： 1322 - 1334 ［ DOI： 10.11834/jig.200682 http://dx.doi.org/10.11834/jig.200682 ］
Tabia H and Laga H . 2015 . Covariance-based descriptors for efficient 3D shape matching， retrieval， and classification . IEEE Transactions on Multimedia ， 17 （ 9 ）： 1591 - 1603 ［ DOI： 10.1109/TMM.2015.2457676 http://dx.doi.org/10.1109/TMM.2015.2457676 ］
Tasse F P ， Kosinka J and Dodgson N . 2015 . Cluster-based point set saliency // IEEE International Conference on Computer Vision . Santiago， Chile ： IEEE： 163 - 171 ［ DOI： 10.1109/ICCV.2015.27 http://dx.doi.org/10.1109/ICCV.2015.27 ］
Tao P P ， Cao J ， Li S ， Liu X P and Liu L G . 2015 . Mesh saliency via ranking unsalient patches in a descriptor space . Computers & Graphics ， 46 ： 264 - 274 ［ DOI： 10.1016/j.cag.2014.09.023 http://dx.doi.org/10.1016/j.cag.2014.09.023 ］
Tao P P ， Zhang L ， Cao J and Liu X . 2016 . Mesh saliency detection based on entropy // International Conference on Digital Home . Guangzhou， China ： IEEE： 288 - 295 ［ DOI： 10.1109/ICDH.2016.065 http://dx.doi.org/10.1109/ICDH.2016.065 ］
Taubin G . 1995a . Estimating the tensor of curvature of a surface from a polyhedral approximation // IEEE International Conference on Computer Vision . Cambridge， USA ： IEEE： 902 - 907 ［ DOI： 10.1109/ICCV.1995.466840 http://dx.doi.org/10.1109/ICCV.1995.466840 ］
Taubin G . 1995b . A signal processing approach to fair surface design // Proceedings of the annual conference on Computer Graphics and Interactive Techniques . New York， USA ： ACM： 351 - 358 ［ DOI： 10.1145/218380.218473 http://dx.doi.org/10.1145/218380.218473 ］
Tavakoli H R and Laaksonen J . 2016 . Bottom-up fixation prediction using unsupervised hierarchical models // Asian Conference on Computer Vision Workshops ， Taipei， China ： Springer： 287 - 302 ［ DOI： 10.1007/978-3-319-54407-6_19 http://dx.doi.org/10.1007/978-3-319-54407-6_19 ］
Tavakoli H R ， Ahmed F ， Borji A and Laaksonen J . 2017 . Saliency revisited： analysis of mouse movements versus fixations // IEEE Conference on Computer Vision and Pattern Recognition . Honolulu， USA ： IEEE： 1774 - 1782 ［ DOI： 10.1109/CVPR.2017.673 http://dx.doi.org/10.1109/CVPR.2017.673 ］
Tliba M ， Kerkouri M A ， Ghariba B ， Chetouani A ， Çöltekin A ， Shehata M S and Bruno A . 2022 . SATSal： a multi-level self-attention based architecture for visual saliency prediction . IEEE Access ， 10 ： 20701 - 20713 ［ DOI： 10.1109/ACCESS.2022.3152189 http://dx.doi.org/10.1109/ACCESS.2022.3152189 ］
Tliba M ， Zhou X M ， Viola I ， Cesar P ， Chetouani A ， Valenzise G and Dufaux F . 2024 . Enhancing immersive experiences through 3D point cloud analysis： a novel framework for applying 2D visual saliency models to 3D point clouds // International Conference on Quality of Multimedia Experience ， Karlshamn， Sweden ： IEEE： 307 - 313 ［ DOI： 10.1109/QoMEX61742.2024.10598254 http://dx.doi.org/10.1109/QoMEX61742.2024.10598254 ］
Tombari F ， Salti S and Stefano L D . 2010 . Unique signatures of histograms for local surface description // European Conference on Computer Vision ， Hersonissos， Greece ： Springer： 356 - 369 ［ DOI： 10.1007/978-3-642-15558-1_26 http://dx.doi.org/10.1007/978-3-642-15558-1_26 ］
Wang H Y ， Luo H ， Wen C L ， Cheng J ， Li P ， Chen Y P ， Wang C and Li J . 2015a . Road boundaries detection based on local normal saliency from mobile laser scanning data . IEEE Geoscience and Remote Sensing Letters ， 12 （ 10 ）： 2085 - 2089 ［ DOI： 10.1109/LGRS.2015.2449074 http://dx.doi.org/10.1109/LGRS.2015.2449074 ］
Wang K P and Zhang C M . 2009 . Content-aware model resizing based on surface deformation . Computers & Graphics ， 33 （ 3 ）： 433 - 438 ［ DOI： 10.1016/j.cag.2009.03.004 http://dx.doi.org/10.1016/j.cag.2009.03.004 ］
Wang S F ， Li N N ， Li S ， Luo Z X ， Su Z X and Qin H . 2015b . Multi-scale mesh saliency based on low-rank and sparse analysis in shape feature space . Computer Aided Geometric Design ， 35 ： 206 - 214 ［ DOI： 10.1016/j.cagd.2015.03.003 http://dx.doi.org/10.1016/j.cagd.2015.03.003 ］
Wang X ， Koch S ， Holmqvist K and Alexa M . 2018 . Tracking the gaze on objects in 3D： how do people really look at the bunny？ ACM Transactions on Graphics ， 37 （ 6 ）： 1 - 18 ［ DOI： 10.1145/3272127.3275094 http://dx.doi.org/10.1145/3272127.3275094 ］
Wang X ， Lindlbauer D ， Lessig C ， Maertens M and Alexa M . 2016 . Measuring the visual salience of 3D printed objects . IEEE Computer Graphics and Applications ， 36 （ 4 ）： 46 - 55 ［ DOI： 10.1109/MCG.2016.47 http://dx.doi.org/10.1109/MCG.2016.47 ］
Wang X D ， Kang F J ， Gu H and Liang H T . 2022 . Regional importance detection of 3D mesh via fusion of local color difference and curvature entropy . International Journal of Modeling， Simulation， and Scientific Computing ， 13 （ 6 ）： 2250060 ［ DOI： 10.1142/S179396232250060X http://dx.doi.org/10.1142/S179396232250060X ］
Wang X D ， Liang H T ， Kang F J and Gu H . 2017 . Multi-scale mesh saliency with local patch weighted curvature entropy . Journal of System Simulation ， 29 （ 9 ）： 1976 - 1983 .
汪小东 ， 梁洪涛 ， 康凤举 ， 顾浩 . 2017 . 基于局部区块加权曲率熵的多尺度网格显著性 . 系统仿真学报 ， 29 （ 9 ）： 1973 - 1983 ［ DOI： 10.16182/j.issn1004731x.joss.201709014 http://dx.doi.org/10.16182/j.issn1004731x.joss.201709014 ］
Wang Z Q ， Zhang Y S ， Yu Y ， Min J and Tian H . 2022 . Review of deep learning based salient object detection . Journal of Image and Graphics ， 27 （ 7 ）： 2112 - 2128 .
王自全 ， 张永生 ， 于英 ， 闵杰 ， 田浩 . 2022 . 深度学习背景下视觉显著性物体检测综述 . 中国图象图形学报 ， 27 （ 7 ）： 2112 - 2128 ［ DOI： 10.11834/jig.200649 http://dx.doi.org/10.11834/jig.200649 ］
Wang Z Y ， Zhang Y J ， Yang Q ， Xu Y L ， Sun J and Liu S . 2023 . Point cloud quality assessment using 3D saliency maps // IEEE International Conference on Visual Communications and Image Processing ， Jeju， Korea ： IEEE： 1 - 5 ［ DOI： 10.1109/VCIP59821.2023.10402711 http://dx.doi.org/10.1109/VCIP59821.2023.10402711 .］
Wei N ， Gao K Y ， Ji R R and Chen P . 2018 . Surface saliency detection based on curvature co-occurrence histograms . IEEE Access ， 6 ： 54536 - 54541 ［ DOI： 10.1109/ACCESS.2018.2872168 http://dx.doi.org/10.1109/ACCESS.2018.2872168 ］
Wu J L ， Shen X Y ， Zhu W and Liu L G . 2013 . Mesh saliency with global rarity . Graphical Models ， 75 （ 5 ）： 255 - 264 ［ DOI： 10.1016/j.gmod.2013.05.002 http://dx.doi.org/10.1016/j.gmod.2013.05.002 ］
Yang B ， Li F W B ， Wang X ， Xu M L ， Liang X H ， Jiang Z Y and Jiang Y H . 2015 . Visual saliency guided textured model simplification . The Visual Computer ， 32 ： 1415 - 1432 ［ DOI： 10.1007/s00371-015-1129-4 http://dx.doi.org/10.1007/s00371-015-1129-4 ］
Yang H ， Chen R ， An S P ， Wei H and Zhang H . 2023 . The growth of image-related three dimensional reconstruction techniques in deep learning-driven era： a critical summary . Journal of Image and Graphics ， 28 （ 8 ）： 2396 - 2409
杨航 ， 陈瑞 ， 安仕鹏 ， 魏豪 ， 张衡 . 2023 . 深度学习背景下的图像三维重建技术进展综述 . 中国图象图形学报 ， 28 （ 8 ）： 2396 - 2409 ［ DOI： 10.11834/jig.220376 http://dx.doi.org/10.11834/jig.220376 ］
Yun J S and Sim J Y . 2016 . Supervoxel-based saliency detection for large-scale colored 3D point clouds // IEEE International Conference on Image Processing ， phoenix， USA ： IEEE： 4062 - 4066 ［ DOI： 10.1109/ICIP.2016.7533123 http://dx.doi.org/10.1109/ICIP.2016.7533123 ］
Zhang Y F ， Li L and Liu G S . 2021 . Adaptive simplification of point cloud based on feature saliency . Computer Engineering and Design ， 42 （ 8 ）： 2212 - 2217
张亦芳 ， 李立 ， 刘光帅 . 2021 . 基于特征显著性的点云自适应精简 . 计算机工程与设计 ， 42 （ 8 ）： 2212 - 2217 ［ DOI： 10.16208/j.issn1000-7024.2021.08.016 http://dx.doi.org/10.16208/j.issn1000-7024.2021.08.016 ］
Zhang Z C ， Sun W ， Min X K ， Wang T ， Liu L and Zhai G T . 2022 . No-reference quality assessment for 3D colored point cloud and mesh models . IEEE Transactions on Circuits and Systems for Video Technology ， 32 （ 11 ）： 7618 - 7631 ［ DOI： 10.1109/TCSVT.2022.3186894 http://dx.doi.org/10.1109/TCSVT.2022.3186894 ］
Zhao Y T ， Liu Y H ， Song R and Zhang M . 2012 . Extended non-local means filter for surface saliency detection // IEEE International Conference on Image Processing . Orlando， USA ： IEEE： 633 - 636 ［ DOI： 10.1109/ICIP.2012.6466939 http://dx.doi.org/10.1109/ICIP.2012.6466939 ］
Zhao Y T ， Liu Y H ， Wang Y J ， Wei B G ， Yang J ， Zhao Y F and Wang Y T . 2016 . Region-based saliency estimation for 3D shape analysis and understanding . Neurocomputing ， 197 ： 1 - 13 ［ DOI： 10.1016/j.neucom.2016.01.012 http://dx.doi.org/10.1016/j.neucom.2016.01.012 ］
Zheng T H ， Chen C Y ， Yuan J S ， Li B and Ren K . 2019 . Pointcloud saliency maps // International Conference on Computer Vision ， Seoul， Korea ： IEEE： 1598 - 1606 ［ DOI： 10.1109/ICCV.2019.00168 http://dx.doi.org/10.1109/ICCV.2019.00168 ］
Zhu J ， Yang L ， Liu W X and Xiao C X . 2014 . Salient features preserved resizing of point-based geometry . Journal of Computer-Aided Design & Computer Graphics ， 26 （ 10 ）： 1624 - 1632
朱建 ， 杨龙 ， 刘维星 ， 肖春霞 . 2014 . 显著性特征保持的点云模型缩放 . 计算机辅助设计与图形学学报 ， 26 （ 10 ）： 1624 - 1632
相关作者
相关机构
京公网安备11010802024621