{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T11:43:51Z","timestamp":1783597431583,"version":"3.55.0"},"reference-count":88,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T00:00:00Z","timestamp":1680566400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["203145Z\/16\/Z"],"award-info":[{"award-number":["203145Z\/16\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Designing realistic digital humans is extremely complex. Most data\u2010driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper, we overcome this limitation by introducing a novel loss function grounded in spectral geometry and applicable to different neural\u2010network\u2010based generative models of 3D head and body meshes. Encouraging the latent variables of mesh variational autoencoders (VAEs) or generative adversarial networks (GANs) to follow the local eigenprojections of identity attributes, we improve latent disentanglement and properly decouple the attribute creation. Experimental results show that our local eigenprojection disentangled (LED) models not only offer improved disentanglement with respect to the state\u2010of\u2010the\u2010art, but also maintain good generation capabilities with training times comparable to the vanilla implementations of the models. Our code and pre\u2010trained models are available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"http:\/\/github.com\/simofoti\/LocalEigenprojDisentangled\">github.com\/simofoti\/LocalEigenprojDisentangled<\/jats:ext-link>.<\/jats:p>","DOI":"10.1111\/cgf.14793","type":"journal-article","created":{"date-parts":[[2023,4,4]],"date-time":"2023-04-04T11:48:57Z","timestamp":1680608937000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["3D Generative Model Latent Disentanglement via Local Eigenprojection"],"prefix":"10.1111","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3207-1965","authenticated-orcid":false,"given":"Simone","family":"Foti","sequence":"first","affiliation":[{"name":"University College London London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bongjin","family":"Koo","sequence":"additional","affiliation":[{"name":"University College London London UK"},{"name":"University of California, Santa Barbara Santa Barbara USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[{"name":"University College London London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew J.","family":"Clarkson","sequence":"additional","affiliation":[{"name":"University College London London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,4,4]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"crossref","unstructured":"[AATDJ23]\u00a0Aumentado\u2010ArmstrongT. TsogkasS. DickinsonS. JepsonA.:Disentangling geometric deformation spaces in generative latent shape models. InInternational Journal of Computer Vision(2023).","DOI":"10.1007\/s11263-023-01750-9"},{"key":"e_1_2_7_3_1","doi-asserted-by":"crossref","unstructured":"[AATJD19]\u00a0Aumentado\u2010ArmstrongT. TsogkasS. JepsonA. DickinsonS.:Geometric disentanglement for generative latent shape models. InProceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE Seoul Korea (South)(2019) pp.\u00a08181\u20138190.","DOI":"10.1109\/ICCV.2019.00827"},{"key":"e_1_2_7_4_1","doi-asserted-by":"crossref","unstructured":"[ABWB19]\u00a0AbrevayaV. F. BoukhaymaA. WuhrerS. BoyerE.:A Decoupled 3D Facial Shape Model by Adversarial Training. In2019 IEEE\/CVF International Conference on Computer Vision (ICCV).IEEE Seoul Korea (South)(Oct2019) pp.\u00a09418\u20139427.","DOI":"10.1109\/ICCV.2019.00951"},{"key":"e_1_2_7_5_1","unstructured":"[ACB17]\u00a0ArjovskyM. ChintalaS. BottouL.:Wasserstein generative adversarial networks. InProceedings of the 34th International Conference on Machine Learning.PrecupD. TehY. W. (Eds.) vol.70ofProceedings of Machine Learning Research PMLR Sydney Australia(Aug2017) pp.\u00a0214\u2013223."},{"key":"e_1_2_7_6_1","unstructured":"[ADMG18]\u00a0AchlioptasP. DiamantiO. MitliagkasI. GuibasL.:Learning representations and generative models for 3d point clouds. InProceedings of the 35th International Conference on Machine Learning.DyJ. KrauseA. (Eds.) vol.80ofProceedings of Machine Learning Research PMLR Stockholm Sweden(July2018) pp.\u00a040\u201349."},{"key":"e_1_2_7_7_1","doi-asserted-by":"crossref","unstructured":"[AW20]\u00a0AlharbiY. WonkaP.:Disentangled image generation through structured noise injection. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE Virtual (2020) pp.\u00a05134\u20135142.","DOI":"10.1109\/CVPR42600.2020.00518"},{"key":"e_1_2_7_8_1","doi-asserted-by":"crossref","unstructured":"[BBP*19]\u00a0BouritsasG. BokhnyakS. PloumpisS. BronsteinM. ZafeiriouS.:Neural 3d morphable models: Spiral convolutional networks for 3d shape representation learning and generation. InProceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE Seoul Korea (South)(2019) pp.\u00a07213\u20137222.","DOI":"10.1109\/ICCV.2019.00731"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_2_7_10_1","doi-asserted-by":"crossref","unstructured":"[BRZ*16]\u00a0BoothJ. RoussosA. ZafeiriouS. PonniahA. DunawayD.:A 3d morphable model learnt from 10 000 faces. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Las Vegas Nevada(2016) pp.\u00a05543\u20135552.","DOI":"10.1109\/CVPR.2016.598"},{"key":"e_1_2_7_11_1","doi-asserted-by":"crossref","unstructured":"[BV99]\u00a0BlanzV. VetterT.:A morphable model for the synthesis of 3d faces. InProceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques. SIGGRAPH '99 ACM Press\/Addison\u2010Wesley Publishing Co. Los Angeles California USA(1999) pp.\u00a0187\u2013194.","DOI":"10.1145\/311535.311556"},{"key":"e_1_2_7_12_1","unstructured":"[BZSL13]\u00a0BrunaJ. ZarembaW. SzlamA. LeCunY.:Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 (2013)."},{"key":"e_1_2_7_13_1","doi-asserted-by":"crossref","unstructured":"[CBGB20]\u00a0ChandranP. BradleyD. GrossM. BeelerT.:Semantic deep face models. In2020 International Conference on 3D Vision (3DV).IEEE Fukuoka Japan(2020) pp.\u00a0345\u2013354.","DOI":"10.1109\/3DV50981.2020.00044"},{"key":"e_1_2_7_14_1","unstructured":"[CBZ*19]\u00a0ChengS. BronsteinM. ZhouY. KotsiaI. PanticM. ZafeiriouS.:Meshgan: Non\u2010linear 3d morphable models of faces. arXiv preprint arXiv:1903.10384 (2019)."},{"key":"e_1_2_7_15_1","volume-title":"Eigenvalues in Riemannian geometry","author":"Chavel I.","year":"1984"},{"key":"e_1_2_7_16_1","doi-asserted-by":"crossref","unstructured":"[CNH*20]\u00a0CosmoL. NorelliA. HalimiO. KimmelR. RodolaE.:Limp: Learning latent shape representations with metric preservation priors. InEuropean Conference on Computer Vision \u2013 ECCV 2020.Springer Springer International Publishing(Online 2020) pp.\u00a019\u201335.","DOI":"10.1007\/978-3-030-58580-8_2"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0057-4"},{"key":"e_1_2_7_18_1","doi-asserted-by":"crossref","unstructured":"[CTS*21]\u00a0ChenH. TangH. ShiH. PengW. SebeN. ZhaoG.:Intrinsic\u2010extrinsic preserved gans for unsupervised 3d pose transfer. InProceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE Virtual (2021) pp.\u00a08630\u20138639.","DOI":"10.1109\/ICCV48922.2021.00851"},{"key":"e_1_2_7_19_1","unstructured":"[DBV16]\u00a0DefferrardM. BressonX. VandergheynstP.:Convolutional neural networks on graphs with fast localized spectral filtering. InProceedings of the 30th International Conference on Neural Information Processing Systems. NIPS'16 Curran Associates Inc. Red Hook NY USA(2016) p.3844\u20133852."},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01260-7"},{"key":"e_1_2_7_21_1","doi-asserted-by":"crossref","unstructured":"[DS19]\u00a0DaiH. ShaoL.:Pointae: Point auto\u2010encoder for 3d statistical shape and texture modelling. InProceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE Seoul Korea (South)(2019) pp.\u00a05410\u20135419.","DOI":"10.1109\/ICCV.2019.00551"},{"key":"e_1_2_7_22_1","doi-asserted-by":"crossref","unstructured":"[DXX*20]\u00a0DingZ. XuY. XuW. ParmarG. YangY. WellingM. TuZ.:Guided variational autoencoder for disentanglement learning. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE Virtual (2020) pp.\u00a07920\u20137929.","DOI":"10.1109\/CVPR42600.2020.00794"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3395208"},{"key":"e_1_2_7_24_1","unstructured":"[EWJ*19]\u00a0EsmaeiliB. WuH. JainS. BozkurtA. SiddharthN. PaigeB. BrooksD. H. DyJ. MeentJ.\u2010W.:Structured disentangled representations. InThe 22nd International Conference on Artificial Intelligence and Statistics.PMLR PMLR Naha Okinawa Japan(2019) pp.\u00a02525\u20132534."},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60365-6_19"},{"key":"e_1_2_7_26_1","doi-asserted-by":"crossref","unstructured":"[FKSC22]\u00a0FotiS. KooB. StoyanovD. ClarksonM. J.:3D shape variational autoencoder latent disentanglement via mini\u2010batch feature swapping for bodies and faces. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE New Orleans Louisiana USA(2022) pp.\u00a018730\u201318739.","DOI":"10.1109\/CVPR52688.2022.01817"},{"key":"e_1_2_7_27_1","doi-asserted-by":"crossref","unstructured":"[GCBZ19]\u00a0GongS. ChenL. BronsteinM. ZafeiriouS.:Spiralnet++: A fast and highly efficient mesh convolution operator. InProceedings of the IEEE\/CVF International Conference on Computer Vision Workshops.IEEE Seoul Korea (South)(2019).","DOI":"10.1109\/ICCVW.2019.00509"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14071"},{"key":"e_1_2_7_29_1","doi-asserted-by":"crossref","unstructured":"[GLP*20]\u00a0GecerB. LattasA. PloumpisS. DengJ. PapaioannouA. MoschoglouS. ZafeiriouS.:Synthesizing coupled 3d face modalities by trunk\u2010branch generative adversarial networks. InEuropean Conference on Computer Vision.Springer IEEE Virtual (2020) pp.\u00a0415\u2013433.","DOI":"10.1007\/978-3-030-58526-6_25"},{"key":"e_1_2_7_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2014.03.008"},{"key":"e_1_2_7_31_1","first-page":"9841","article-title":"Ganspace: Discovering interpretable gan controls","volume":"33","author":"H\u00e4rk\u00f6nen E.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_7_32_1","doi-asserted-by":"crossref","unstructured":"[HHS*21]\u00a0HuangQ. HuangX. SunB. ZhangZ. JiangJ. BajajC.:Arapreg: An as\u2010rigid\u2010as possible regularization loss for learning deformable shape generators. InProceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE Virtual (2021) pp.\u00a05815\u20135825.","DOI":"10.1109\/ICCV48922.2021.00576"},{"key":"e_1_2_7_33_1","unstructured":"[HMP*17]\u00a0HigginsI. MattheyL. PalA. BurgessC. GlorotX. BotvinickM. MohamedS. LerchnerA.:beta\u2010VAE: Learning basic visual concepts with a constrained variational framework. InInternational Conference on Learning Representations.Toulon France(2017)."},{"key":"e_1_2_7_34_1","doi-asserted-by":"crossref","unstructured":"[HMWL22]\u00a0HuangX. MallyaA. WangT.\u2010C. LiuM.\u2010Y.:Multimodal conditional image synthesis with product\u2010of\u2010experts gans. InEuropean Conference on Computer Vision.Springer International Tel Aviv Israel(2022).","DOI":"10.1007\/978-3-031-19787-1_6"},{"key":"e_1_2_7_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916751"},{"key":"e_1_2_7_36_1","doi-asserted-by":"crossref","unstructured":"[JWCZ19]\u00a0JiangZ.\u2010H. WuQ. ChenK. ZhangJ.:Disentangled representation learning for 3d face shape. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE Long Beach California USA(2019) pp.\u00a011957\u201311966.","DOI":"10.1109\/CVPR.2019.01223"},{"key":"e_1_2_7_37_1","unstructured":"[KAL*21]\u00a0KarrasT. AittalaM. LaineS. H\u00e4rk\u00f6nenE. HellstenJ. LehtinenJ. AilaT.:Alias\u2010free generative adversarial networks. InAdvances in Neural Information Processing Systems.Curran Associates Inc. (2021) vol.34 pp.\u00a0852\u2013863."},{"key":"e_1_2_7_38_1","unstructured":"[KM18]\u00a0KimH. MnihA.:Disentangling by factorising. InInternational Conference on Machine Learning.PMLR Stockholm Sweden(2018) pp.\u00a02649\u20132658."},{"key":"e_1_2_7_39_1","unstructured":"[KSB18]\u00a0KumarA. SattigeriP. BalakrishnanA.:Variational inference of disentangled latent concepts from unlabeled observations. InInternational Conference on Learning Representations.Vancouver Canada(2018)."},{"key":"e_1_2_7_40_1","unstructured":"[KW14]\u00a0KingmaD. P. WellingM.:Auto\u2010encoding variational bayes. InInternational Conference on Learning Representations.Banff Canada(2014)."},{"key":"e_1_2_7_41_1","unstructured":"[KWKT15]\u00a0KulkarniT. D. WhitneyW. F. KohliP. TenenbaumJ.:Deep convolutional inverse graphics network. InAdvances in Neural Information Processing Systems.CortesC. LawrenceN. LeeD. SugiyamaM. GarnettR. (Eds.) Curran Associates Inc. Montreal Canada(2015) vol.28."},{"issue":"8","key":"e_1_2_7_42_1","first-page":"2","article-title":"Practice and theory of blendshape facial models","volume":"1","author":"Lewis J. P.","year":"2014","journal-title":"Eurographics (State of the Art Reports)"},{"key":"e_1_2_7_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_2_7_44_1","doi-asserted-by":"crossref","unstructured":"[LBBM18]\u00a0LitanyO. BronsteinA. BronsteinM. MakadiaA.:Deformable shape completion with graph convolutional autoencoders. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Salt Lake City Utah USA(2018) pp.\u00a01886\u20131895.","DOI":"10.1109\/CVPR.2018.00202"},{"key":"e_1_2_7_45_1","doi-asserted-by":"crossref","unstructured":"[LBZ*20]\u00a0LiR. BladinK. ZhaoY. ChinaraC. IngrahamO. XiangP. RenX. PrasadP. KishoreB. XingJ. et\u00a0al.:Learning formation of physically\u2010based face attributes. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.CVPR Virtual (2020) pp.\u00a03410\u20133419.","DOI":"10.1109\/CVPR42600.2020.00347"},{"key":"e_1_2_7_46_1","unstructured":"[LKL*21]\u00a0LingH. KreisK. LiD. KimS. W. TorralbaA. FidlerS.:Editgan: High\u2010precision semantic image editing. InAdvances in Neural Information Processing Systems.Curran Associates Inc. Virtual (2021) vol.34 pp.\u00a016331\u201316345."},{"key":"e_1_2_7_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459852"},{"key":"e_1_2_7_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20027"},{"key":"e_1_2_7_49_1","doi-asserted-by":"crossref","unstructured":"[LLWL20]\u00a0LeeC.\u2010H. LiuZ. WuL. LuoP.:Maskgan: Towards diverse and interactive facial image manipulation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE Virtual (2020) pp.\u00a05549\u20135558.","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"e_1_2_7_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_2_7_51_1","doi-asserted-by":"crossref","unstructured":"[LYF*21]\u00a0LombardiS. YangB. FanT. BaoH. ZhangG. PollefeysM. CuiZ.:Latenthuman: Shape\u2010and\u2010pose disentangled latent representation for human bodies. In2021 International Conference on 3D Vision (3DV).IEEE Virtual (2021) pp.\u00a0278\u2013288.","DOI":"10.1109\/3DV53792.2021.00038"},{"key":"e_1_2_7_52_1","doi-asserted-by":"publisher","DOI":"10.1093\/bjps\/axs046"},{"key":"e_1_2_7_53_1","doi-asserted-by":"crossref","unstructured":"[MLX*17]\u00a0MaoX. LiQ. XieH. LauR. Y. WangZ. Paul SmolleyS.:Least squares generative adversarial networks. InProceedings of the IEEE International Conference on Computer Vision.IEEE Venice Italy(2017) pp.\u00a02794\u20132802.","DOI":"10.1109\/ICCV.2017.304"},{"key":"e_1_2_7_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01329-8"},{"key":"e_1_2_7_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01492-6"},{"key":"e_1_2_7_56_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13240"},{"key":"e_1_2_7_57_1","doi-asserted-by":"crossref","unstructured":"[OBB20]\u00a0OsmanA. A. A. BolkartT. BlackM. J.:STAR: A sparse trained articulated human body regressor. InEuropean Conference on Computer Vision (ECCV).Springer International Publishing Virtual (2020) pp.\u00a0598\u2013613.","DOI":"10.1007\/978-3-030-58539-6_36"},{"key":"e_1_2_7_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2022.12.004"},{"key":"e_1_2_7_59_1","doi-asserted-by":"crossref","unstructured":"[OFD*22]\u00a0OtberdoutN. FerrariC. DaoudiM. BerrettiS. Del BimboA.:Sparse to dense dynamic 3d facial expression generation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE New Orleans Louisiana USA(2022) pp.\u00a020385\u201320394.","DOI":"10.1109\/CVPR52688.2022.01974"},{"key":"e_1_2_7_60_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-02411-y"},{"key":"e_1_2_7_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766993"},{"key":"e_1_2_7_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991150"},{"key":"e_1_2_7_63_1","doi-asserted-by":"crossref","unstructured":"[PWP*19]\u00a0PloumpisS. WangH. PearsN. SmithW. A. ZafeiriouS.:Combining 3d morphable models: A large scale face\u2010and\u2010head model. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Long Beach California USA(2019) pp.\u00a010934\u201310943.","DOI":"10.1109\/CVPR.2019.01119"},{"key":"e_1_2_7_64_1","doi-asserted-by":"crossref","unstructured":"[RBSB18]\u00a0RanjanA. BolkartT. SanyalS. BlackM. J.:Generating 3d faces using convolutional mesh autoencoders. InProceedings of the European Conference on Computer Vision (ECCV).Springer International Publishing Munich Germany(2018) pp.\u00a0704\u2013720.","DOI":"10.1007\/978-3-030-01219-9_43"},{"key":"e_1_2_7_65_1","doi-asserted-by":"crossref","unstructured":"[RDC*21]\u00a0RobertsD. DanielyanA. ChuH. Golparvar\u2010FardM. ForsythD.:Lsd\u2010structurenet: Modeling levels of structural detail in 3d part hierarchies. InProceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE Virtual (2021) pp.\u00a05836\u20135845.","DOI":"10.1109\/ICCV48922.2021.00578"},{"key":"e_1_2_7_66_1","unstructured":"[RKH*21]\u00a0RadfordA. KimJ. W. HallacyC. RameshA. GohG. AgarwalS. SastryG. AskellA. MishkinP. ClarkJ. KruegerG. SutskeverI.:Learning transferable visual models from natural language supervision. InProceedings of the 38th International Conference on Machine Learning.MeilaM. ZhangT. (Eds.) vol.139ofProceedings of Machine Learning Research PMLR Virtual (2021) pp.\u00a08748\u20138763."},{"key":"e_1_2_7_67_1","unstructured":"[RL21]\u00a0RhodesT. LeeD.:Local disentanglement in variational auto\u2010encoders using jacobianl_1$ l\\_1$regularization. InAdvances in Neural Information Processing Systems.Curran Associates Inc. Virtual(2021) vol.34."},{"key":"e_1_2_7_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2005.10.011"},{"key":"e_1_2_7_69_1","doi-asserted-by":"crossref","unstructured":"[SBKM21]\u00a0ShoshanA. BhonkerN. KviatkovskyI. MedioniG.:Gan\u2010control: Explicitly controllable gans. InProceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE Virtual (2021) pp.\u00a014083\u201314093.","DOI":"10.1109\/ICCV48922.2021.01382"},{"key":"e_1_2_7_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"e_1_2_7_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"e_1_2_7_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964971"},{"key":"e_1_2_7_73_1","unstructured":"[TSL21]\u00a0TatroN. J. SchonsheckS. C. LaiR.:Unsupervised geometric disentanglement via CFAN\u2010VAE.ICLR Workshop on Geometrical and Topological Representation Learning. Virtual (2021)."},{"key":"e_1_2_7_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085887"},{"key":"e_1_2_7_75_1","unstructured":"[VB20]\u00a0VoynovA. BabenkoA.:Unsupervised discovery of interpretable directions in the gan latent space. InInternational Conference on Machine Learning.PMLR PMLR Virtual (2020) pp.\u00a09786\u20139796."},{"key":"e_1_2_7_76_1","doi-asserted-by":"crossref","unstructured":"[VRM*17]\u00a0VarolG. RomeroJ. MartinX. MahmoodN. BlackM. J. LaptevI. SchmidC.:Learning from synthetic humans. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Honolulu Hawaii USA(2017) pp.\u00a0109\u2013117.","DOI":"10.1109\/CVPR.2017.492"},{"key":"e_1_2_7_77_1","unstructured":"[WDH*19]\u00a0WangW. DangZ. HuY. FuaP. SalzmannM.:Backpropagation\u2010friendly eigendecomposition. InAdvances in Neural Information Processing Systems. Virtual (2019) vol.32."},{"key":"e_1_2_7_78_1","unstructured":"[WYH*21]\u00a0WangT. YueZ. HuangJ. SunQ. ZhangH.:Self\u2010supervised learning disentangled group representation as feature. InAdvances in Neural Information Processing Systems.Curran Associates Inc. Virtual (2021) vol.34."},{"key":"e_1_2_7_79_1","doi-asserted-by":"crossref","unstructured":"[YFST18]\u00a0YangY. FengC. ShenY. TianD.:Foldingnet: Point cloud auto\u2010encoder via deep grid deformation. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Salt Lake City Utah USA(2018) pp.\u00a0206\u2013215.","DOI":"10.1109\/CVPR.2018.00029"},{"key":"e_1_2_7_80_1","doi-asserted-by":"crossref","unstructured":"[YHH*19]\u00a0YangG. HuangX. HaoZ. LiuM.\u2010Y. BelongieS. HariharanB.:Pointflow: 3d point cloud generation with continuous normalizing flows. InProceedings of the IEEE\/CVF International Conference on Computer Vision.IEEE Seoul Korea (South)(2019) pp.\u00a04541\u20134550.","DOI":"10.1109\/ICCV.2019.00464"},{"key":"e_1_2_7_81_1","doi-asserted-by":"crossref","unstructured":"[YLY*20]\u00a0YuanY.\u2010J. LaiY.\u2010K. YangJ. DuanQ. FuH. GaoL.:Mesh variational autoencoders with edge contraction pooling. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops.IEEE Virtual (2020) pp.\u00a0274\u2013275.","DOI":"10.1109\/CVPRW50498.2020.00145"},{"key":"e_1_2_7_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526212"},{"key":"e_1_2_7_83_1","doi-asserted-by":"crossref","unstructured":"[ZBPM20]\u00a0ZhouK. BhatnagarB. L. Pons\u2010MollG.:Unsupervised shape and pose disentanglement for 3d meshes. InEuropean Conference on Computer Vision.Springer Springer International Publishing Virtual (2020) pp.\u00a0341\u2013357.","DOI":"10.1007\/978-3-030-58542-6_21"},{"key":"e_1_2_7_84_1","doi-asserted-by":"crossref","unstructured":"[ZKJB17]\u00a0ZuffiS. KanazawaA. JacobsD. W. BlackM. J.:3d menagerie: Modeling the 3d shape and pose of animals. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Honolulu Hawaii USA(2017) pp.\u00a06365\u20136373.","DOI":"10.1109\/CVPR.2017.586"},{"key":"e_1_2_7_85_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2010.01655.x"},{"key":"e_1_2_7_86_1","first-page":"9251","article-title":"Fully convolutional mesh autoencoder using efficient spatially varying kernels","volume":"33","author":"Zhou Y.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_7_87_1","doi-asserted-by":"crossref","unstructured":"[ZXT20]\u00a0ZhuX. XuC. TaoD.:Learning disentangled representations with latent variation predictability. InEuropean Conference on Computer Vision.Springer International Publishing Virtual (2020) pp.\u00a0684\u2013700.","DOI":"10.1007\/978-3-030-58607-2_40"},{"key":"e_1_2_7_88_1","doi-asserted-by":"crossref","unstructured":"[ZYHC22]\u00a0ZhengM. YangH. HuangD. ChenL.:Imface: A nonlinear 3d morphable face model with implicit neural representations. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE New Orleans Louisiana USA(2022) pp.\u00a020343\u201320352.","DOI":"10.1109\/CVPR52688.2022.01970"},{"key":"e_1_2_7_89_1","doi-asserted-by":"crossref","unstructured":"[ZYL*20]\u00a0ZhangZ. YuC. LiH. SunJ. LiuF.:Learning distribution independent latent representation for 3d face disentanglement. In2020 International Conference on 3D Vision (3DV).IEEE Virtual (2020) pp.\u00a0848\u2013857.","DOI":"10.1109\/3DV50981.2020.00095"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.14793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T16:52:31Z","timestamp":1718556751000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.14793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,4]]},"references-count":88,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["10.1111\/cgf.14793"],"URL":"https:\/\/doi.org\/10.1111\/cgf.14793","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,4]]},"assertion":[{"value":"2023-04-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e14793"}}