{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T08:15:26Z","timestamp":1774685726573,"version":"3.50.1"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2019,6,3]],"date-time":"2019-06-03T00:00:00Z","timestamp":1559520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"H2020 Marie Sk?odowska-Curie Actions","award":["642841"],"award-info":[{"award-number":["642841"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Comput. Graph. Interact. Tech."],"published-print":{"date-parts":[[2019,6,3]]},"abstract":"<jats:p>We propose, DeepPRT, a deep convolutional neural network to compactly encapsulate the radiance transfer of a freely deformable object for rasterization in real-time.<\/jats:p>\n          <jats:p>With pre-computation of radiance transfer (PRT) we can store complex light interactions appropriate to the shape of a given object at each surface point for subsequent real-time rendering via fast linear algebra evaluation against the viewing direction and distant light environment. However, performing light transport projection into an efficient basis representation, such as Spherical Harmonics (SH), requires a numerical Monte Carlo integration computation, limiting usage to rigid only objects or highly constrained deformation sequences. The bottleneck, when considering freely deformable objects, is the heavy memory requirement to wield all pre-computations in rendering with global illumination results. We present a compact representation of PRT for deformable objects with fixed memory consumption, which solves diverse non-linear deformations and is shown to be effective beyond the input training set. Specifically, a U-Net is trained to predict the coefficients of the transfer function (SH coefficients in this case), for a given animation's shape query each frame in real-time.<\/jats:p>\n          <jats:p>We contribute deep learning of PRT within a parametric surface space representation via geometry images using harmonic mapping with a texture space filling energy minimization variant. This surface representation facilitates the learning procedure, removing irrelevant, deformation invariant information; and supports standard convolution operations. Finally, comparisons with ground truth and a recent linear morphable-model method is provided.<\/jats:p>","DOI":"10.1145\/3320284","type":"journal-article","created":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T16:01:38Z","timestamp":1559664098000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep Precomputed Radiance Transfer for Deformable Objects"],"prefix":"10.1145","volume":"2","author":[{"given":"Yue","family":"Li","sequence":"first","affiliation":[{"name":"University of Pennsylvania"}]},{"given":"Pablo","family":"Wiedemann","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University"}]},{"given":"Kenny","family":"Mitchell","sequence":"additional","affiliation":[{"name":"Edinburgh Napier University"}]}],"member":"320","published-online":{"date-parts":[[2019,6,3]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_2_1_2_1","volume-title":"Bronstein","author":"Boscaini Davide","year":"2016"},{"key":"e_1_2_1_3_1","volume-title":"Geometric deep learning: going beyond Euclidean data. CoRR abs\/1611.08097","author":"Bronstein Michael M.","year":"2016"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073601"},{"key":"e_1_2_1_5_1","volume-title":"A Survey of Model Compression and Acceleration for Deep Neural Networks. CoRR abs\/1710.09282","author":"Cheng Yu","year":"2017"},{"key":"e_1_2_1_6_1","unstructured":"Fran\u00e7ois Chollet et al. 2015. Keras. https:\/\/keras.io.  Fran\u00e7ois Chollet et al. 2015. Keras. https:\/\/keras.io."},{"key":"e_1_2_1_7_1","volume-title":"Radiosity and Realistic Image Synthesis","author":"Cohen Michael F."},{"key":"e_1_2_1_8_1","volume-title":"Deformable Convolutional Networks. CoRR abs\/1703.06211","author":"Dai Jifeng","year":"2017"},{"key":"e_1_2_1_9_1","volume-title":"Deep Diffeomorphic Transformer Networks. Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Detlefsen Nicki Skafte","year":"2018"},{"key":"e_1_2_1_10_1","doi-asserted-by":"crossref","unstructured":"James Eells and J. H. Sampson. 1964. Harmonic mappings of Riemannian manifords. The Johns Hopkins University Press. 86:109--160 pages.  James Eells and J. H. Sampson. 1964. Harmonic mappings of Riemannian manifords. The Johns Hopkins University Press. 86:109--160 pages.","DOI":"10.2307\/2373037"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2383847.2383853"},{"key":"e_1_2_1_12_1","unstructured":"David Gu. 2018. Harmonic Map. https:\/\/www3.cs.stonybrook.edu\/~gu\/tutorial\/HarmonicMap.html Accessed: 28-11-2018.  David Gu. 2018. Harmonic Map. https:\/\/www3.cs.stonybrook.edu\/~gu\/tutorial\/HarmonicMap.html Accessed: 28-11-2018."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566589"},{"key":"e_1_2_1_14_1","volume-title":"Dally","author":"Han Song","year":"2015"},{"key":"e_1_2_1_15_1","volume-title":"Deep Residual Learning for Image Recognition. CoRR abs\/1512.03385","author":"He Kaiming","year":"2015"},{"key":"e_1_2_1_16_1","volume-title":"Deep-learning the Latent Space of Light Transport. arXiv abs\/1811.04756","author":"Hermosilla Pedro","year":"2018"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882359"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/581896.581934"},{"key":"e_1_2_1_21_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014"},{"key":"e_1_2_1_22_1","volume-title":"Proceedings of the 25th International Conference on Neural Information Processing Systems -","volume":"1","author":"Krizhevsky Alex"},{"key":"e_1_2_1_23_1","volume-title":"Hinton","author":"LeCun Yann","year":"2015"},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Yunze Man Yangsibo Huang Junyi Feng Xi Li and Fei Wu. 2018. Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net.  Yunze Man Yangsibo Huang Junyi Feng Xi Li and Fei Wu. 2018. Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net.","DOI":"10.1109\/TMI.2019.2911588"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073616"},{"key":"e_1_2_1_26_1","volume-title":"ShapeNet: Convolutional Neural Networks on Non-Euclidean Manifolds. CoRR abs\/1501.06297","author":"Masci Jonathan","year":"2015"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988458.2988485"},{"key":"e_1_2_1_28_1","unstructured":"Federico Monti. 2018. Geometric Deep Learning. http:\/\/geometricdeeplearning.com\/ Accessed: 26-11-2018.  Federico Monti. 2018. Geometric Deep Learning. http:\/\/geometricdeeplearning.com\/ Accessed: 26-11-2018."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13225"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882280"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882274"},{"key":"e_1_2_1_32_1","volume-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation. CoRR abs\/1505.04597","author":"Ronneberger Olaf","year":"2015"},{"key":"e_1_2_1_33_1","volume-title":"Efficient Global Illumination for Morphable Models. In 2017 IEEE International Conference on Computer Vision (ICCV). 3885--3893","author":"Schneider A."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_14"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566612"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073335"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3283254.3283281"},{"key":"e_1_2_1_38_1","volume-title":"Riedmiller","author":"Springenberg Jost Tobias","year":"2014"},{"key":"e_1_2_1_39_1","volume-title":"Deep Illumination: Approximating Dynamic Global Illumination with Generative Adversarial Network. CoRR abs\/1710.09834","author":"Thomas Manu Mathew","year":"2017"},{"key":"e_1_2_1_40_1","volume-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1912--1920","author":"Wu Zhirong"}],"container-title":["Proceedings of the ACM on Computer Graphics and Interactive Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3320284","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3320284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:28Z","timestamp":1750200088000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3320284"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,3]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,6,3]]}},"alternative-id":["10.1145\/3320284"],"URL":"https:\/\/doi.org\/10.1145\/3320284","relation":{},"ISSN":["2577-6193"],"issn-type":[{"value":"2577-6193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,3]]},"assertion":[{"value":"2019-06-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}