{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T22:39:08Z","timestamp":1770676748887,"version":"3.49.0"},"reference-count":55,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T00:00:00Z","timestamp":1622764800000},"content-version":"vor","delay-in-days":34,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2021,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the lack of closed\u2010form expressions, which requires a costly search involving rendering. To overcome these limitations we propose to separate viewpoint selection from rendering through an end\u2010to\u2010end learning approach, whereby we reduce the influence of the mesh quality by predicting viewpoints from unstructured point clouds instead of polygonal meshes. While this makes our approach insensitive to the mesh discretization during evaluation, it only becomes possible when resolving label ambiguities that arise in this context. Therefore, we additionally propose to incorporate the label generation into the training procedure, making the label decision adaptive to the current network predictions. We show how our proposed approach allows for learning viewpoint predictions for models from different object categories and for different viewpoint qualities. Additionally, we show that prediction times are reduced from several minutes to a fraction of a second, as compared to state\u2010of\u2010the\u2010art (SOTA) viewpoint quality evaluation. Code and training data is available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/schellmi42\/viewpoint_learning\">https:\/\/github.com\/schellmi42\/viewpoint_learning<\/jats:ext-link>, which is to our knowledge the biggest viewpoint quality dataset available.<\/jats:p>","DOI":"10.1111\/cgf.142643","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T16:37:32Z","timestamp":1622824652000},"page":"413-423","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enabling Viewpoint Learning through Dynamic Label Generation"],"prefix":"10.1111","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5294-4474","authenticated-orcid":false,"given":"M.","family":"Schelling","sequence":"first","affiliation":[{"name":"Ulm University  Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3586-4741","authenticated-orcid":false,"given":"P.","family":"Hermosilla","sequence":"additional","affiliation":[{"name":"Ulm University  Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4638-4065","authenticated-orcid":false,"given":"P.\u2010P.","family":"V\u00e1zquez","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya  Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-5512","authenticated-orcid":false,"given":"T.","family":"Ropinski","sequence":"additional","affiliation":[{"name":"Ulm University  Germany"}]}],"member":"311","published-online":{"date-parts":[[2021,6,4]]},"reference":[{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2004.00781.x"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/e20050370"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"BordoloiU. D. ShenH.-W.: View selection for volume rendering. InVIS 05. IEEE Visualization 2005. (Oct2005) pp.487\u2013494. doi:10.1109\/VISUAL.2005.1532833. 2","DOI":"10.1109\/VISUAL.2005.1532833"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1068\/p2897"},{"key":"e_1_2_9_6_2","doi-asserted-by":"crossref","unstructured":"CoronaE. KunduK. FidlerS.: Pose estimation for objects with rotational symmetry. In2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)(Oct2018) pp.7215\u20137222. 3","DOI":"10.1109\/IROS.2018.8594282"},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"DutagaciH. CheungC. P. GodilA.: A benchmark for best view selection of 3D objects. InProceedings of the ACM workshop on 3D object retrieval(2010) pp.45\u201350. 4 9","DOI":"10.1145\/1877808.1877819"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"DeinzerF. DerichsC. NiemannH. DenzlerJ.: Integrated viewpoint fusion and viewpoint selection for optimal object recognition. InBMVC(2006) pp.287\u2013296. 2","DOI":"10.5244\/C.20.30"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001409007351"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.623193"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/1462055.1462056"},{"key":"e_1_2_9_12_2","first-page":"53","article-title":"Comparison and evaluation of viewpoint quality estimation algorithms for immersive virtual environments","volume":"15","author":"Freitag S.","year":"2015","journal-title":"ICAT-EGVE"},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"FreitagS. WeyersB. KuhlenT. W.: Assisted travel based on common visibility and navigation meshes. In2017 IEEE Virtual Reality (VR)(2017) IEEE pp.369\u2013370. 2","DOI":"10.1109\/VR.2017.7892330"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11004-009-9257-x"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"GumholdS.: Maximum entropy light source placement. InProceedings of IEEE Visualization Conference(oct2002) pp.275\u2013282. doi:10.1109\/VISUAL.2002.1183785. 2","DOI":"10.1109\/VISUAL.2002.1183785"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2689998"},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"HermosillaP. RitschelT. V\u00e1zquezP.-P. Vinacua\u00c0. RopinskiT.: Monte carlo convolution for learning on non-uniformly sampled point clouds. InSIGGRAPH Asia 2018 Technical Papers(2018) ACM p.235. 5 6","DOI":"10.1145\/3272127.3275110"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"HeinrichJ. VuongJ. HammangC. J. WuA. RittenbruchM. HoganJ. BreretonM. O'DonoghueS. I.: Evaluating viewpoint entropy for ribbon representation of protein structure. InComputer Graphics Forum(2016) vol. 35 Wiley Online Library pp.181\u2013190. 1 2","DOI":"10.1111\/cgf.12894"},{"key":"e_1_2_9_19_2","unstructured":"HeJ. WangL. ZhouW. ZhangH. CuiX. GuoY.:Viewpoint selection for photographing architectures 2017. arXiv:1703.01702. 1"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. SunJ.: Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition(2016) pp.770\u2013778. 7","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"e_1_2_9_22_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_2_9_23_2","unstructured":"KingmaD. BaJ.: Adam: A method for stochastic optimization.International Conference on Learning Representations(122014). 6"},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"KimS.-h. TaiY.-W. LeeJ.-Y. ParkJ. KweonI. S.: Category-specific salient view selection via deep convolutional neural networks. InComputer Graphics Forum(2017) vol. 36 Wiley Online Library pp.313\u2013328. 2","DOI":"10.1111\/cgf.13082"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766965"},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"LiuC.-a. DongR.-f. WuH.: Flying robot based viewpoint selection for the electricity transmission equipment inspection.Mathematical Problems in Engineering 2014(2014). doi:10.1155\/2014\/783810. 2","DOI":"10.1155\/2014\/783810"},{"key":"e_1_2_9_27_2","doi-asserted-by":"crossref","unstructured":"LiaoS. GavvesE. SnoekC. G.: Spherical regression: Learning viewpoints surface normals and 3D rotations on n-spheres. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2019) pp.9759\u20139767. 2 3 7 9","DOI":"10.1109\/CVPR.2019.00999"},{"key":"e_1_2_9_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073244"},{"key":"e_1_2_9_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.gmod.2016.03.001"},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.745736"},{"key":"e_1_2_9_31_2","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1007\/978-3-662-54345-0_79","volume-title":"Bildverarbeitung fuer die Medizin 2017","author":"Meuschke M.","year":"2017"},{"key":"e_1_2_9_32_2","unstructured":"M\u00fchlerK. NeugebauerM. TietjenC. PreimB.: Viewpoint selection for intervention planning. InEuroVis(2007) pp.267\u2013274. 2"},{"key":"e_1_2_9_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21608-4_8"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356498"},{"key":"e_1_2_9_35_2","first-page":"7891","article-title":"Rendernet: A deep convolutional network for differentiable rendering from 3d shapes","volume":"31","author":"Nguyen-Phuoc T. H.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_36_2","unstructured":"PlemenosD. BenayadaM.: Intelligent display in scene modeling. new techniques to automatically compute good views. InInternational Conference GraphiCon(1996) vol. 96 pp.1\u20135. 3"},{"key":"e_1_2_9_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-005-0326-y"},{"key":"e_1_2_9_38_2","unstructured":"QiC. R. YiL. SuH. GuibasL. J.:Pointnet++: Deep hierarchical feature learning on point sets in a metric space 2017. arXiv:1706.02413. 6 8 9"},{"key":"e_1_2_9_39_2","doi-asserted-by":"crossref","unstructured":"RupprechtC. LainaI. DiPietroR. BaustM.: Learning in an uncertain world: Representing ambiguity through multiple hypotheses. In2017 IEEE International Conference on Computer Vision (ICCV)(Oct2017) pp.3611\u20133620. 3","DOI":"10.1109\/ICCV.2017.388"},{"key":"e_1_2_9_40_2","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2019627.2019628"},{"key":"e_1_2_9_42_2","doi-asserted-by":"crossref","unstructured":"SaranA. LakicB. MajumdarS. HessJ. NiekumS.: Viewpoint selection for visual failure detection. In2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)(Sep.2017) pp.5437\u20135444. doi:10.1109\/IROS.2017.8206439. 2","DOI":"10.1109\/IROS.2017.8206439"},{"key":"e_1_2_9_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2530691"},{"key":"e_1_2_9_44_2","unstructured":"SmithN. MoehrleN. GoeseleM. HeidrichW.: Aerial path planning for urban scene reconstruction: A continuous optimization method and benchmark. InSIGGRAPH Asia 2018 Technical Papers(2018) ACM p.183. 2"},{"key":"e_1_2_9_45_2","unstructured":"SbertM. PlemenosD. FeixasM. Gonz\u00e1lezF.: Viewpoint quality: Measures and applications. InComputational Aesthetics in Graphics Visualization and Imaging(012005) pp.185\u2013192. doi:10.2312\/COMPAESTH\/COMPAESTH05\/185-192. 3"},{"issue":"3","key":"e_1_2_9_46_2","first-page":"27","article-title":"CNNs based viewpoint estimation for volume visualization","volume":"10","author":"Shi N.","year":"2019","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"e_1_2_9_47_2","doi-asserted-by":"crossref","unstructured":"SzegedyC. WeiLiu YangqingJia SermanetP. ReedS. AnguelovD. ErhanD. VanhouckeV. RabinovichA.: Going deeper with convolutions. In2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(June2015) pp.1\u20139. doi:10.1109\/CVPR.2015.7298594. 6","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_9_48_2","unstructured":"TaoY. LinH. BaoH. DongF. ClapworthyG.: Structure-aware viewpoint selection for volume visualization. In2009 IEEE Pacific Visualization Symposium(2009) IEEE pp.193\u2013200. 2"},{"key":"e_1_2_9_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2006.152"},{"key":"e_1_2_9_50_2","unstructured":"V\u00e1zquezP.-P. FeixasM. SbertM. HeidrichW.: Viewpoint selection using viewpoint entropy. InVMV(2001) vol. 1 pp.273\u2013280. 3"},{"key":"e_1_2_9_51_2","unstructured":"V\u00e1zquezP.-P. FeixasM. SbertM. LlobetA.: Viewpoint entropy: a new tool for obtaining good views of molecules. InACM International Conference Proceeding Series(2002) vol. 22 pp.183\u2013188. 2"},{"key":"e_1_2_9_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-008-0251-4"},{"key":"e_1_2_9_53_2","unstructured":"WuZ. SongS. KhoslaA. YuF. ZhangL. TangX. XiaoJ.: 3D shapenets: A deep representation for volumetric shapes. InProceedings of the IEEE conference on computer vision and pattern recognition(2015) pp.1912\u20131920. 6"},{"key":"e_1_2_9_54_2","article-title":"Intelligent volume visualization through transfer function and viewpoint selection [j]","volume":"5","author":"Yao W. Y. Z.","year":"2008","journal-title":"Journal of Computer-Aided Design & Computer Graphics"},{"key":"e_1_2_9_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12650-019-00583-4"},{"key":"e_1_2_9_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3001230"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.142643","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.142643","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.142643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T10:39:17Z","timestamp":1692873557000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.142643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["10.1111\/cgf.142643"],"URL":"https:\/\/doi.org\/10.1111\/cgf.142643","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]},"assertion":[{"value":"2021-06-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}