{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:07:39Z","timestamp":1784268459728,"version":"3.55.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2013,7,21]],"date-time":"2013-07-21T00:00:00Z","timestamp":1374364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2013,7,21]]},"abstract":"<jats:p>We present radiance regression functions for fast rendering of global illumination in scenes with dynamic local light sources. A radiance regression function (RRF) represents a non-linear mapping from local and contextual attributes of surface points, such as position, viewing direction, and lighting condition, to their indirect illumination values. The RRF is obtained from precomputed shading samples through regression analysis, which determines a function that best fits the shading data. For a given scene, the shading samples are precomputed by an offline renderer.<\/jats:p>\n          <jats:p>The key idea behind our approach is to exploit the nonlinear coherence of the indirect illumination data to make the RRF both compact and fast to evaluate. We model the RRF as a multilayer acyclic feed-forward neural network, which provides a close functional approximation of the indirect illumination and can be efficiently evaluated at run time. To effectively model scenes with spatially variant material properties, we utilize an augmented set of attributes as input to the neural network RRF to reduce the amount of inference that the network needs to perform. To handle scenes with greater geometric complexity, we partition the input space of the RRF model and represent the subspaces with separate, smaller RRFs that can be evaluated more rapidly. As a result, the RRF model scales well to increasingly complex scene geometry and material variation. Because of its compactness and ease of evaluation, the RRF model enables real-time rendering with full global illumination effects, including changing caustics and multiple-bounce high-frequency glossy interreflections.<\/jats:p>","DOI":"10.1145\/2461912.2462009","type":"journal-article","created":{"date-parts":[[2013,7,16]],"date-time":"2013-07-16T18:06:45Z","timestamp":1373998005000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":90,"title":["Global illumination with radiance regression functions"],"prefix":"10.1145","volume":"32","author":[{"given":"Peiran","family":"Ren","sequence":"first","affiliation":[{"name":"Tsinghua University and Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaping","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minmin","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Tong","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baining","family":"Guo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia and Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2013,7,21]]},"reference":[{"key":"e_1_2_2_1_1","unstructured":"Beale M. H. Hagan M. T. and Demuth H. B. 2012. Neural Network Toolbox user's guide.  Beale M. H. Hagan M. T. and Demuth H. B. 2012. Neural Network Toolbox user's guide ."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90047-9"},{"key":"e_1_2_2_3_1","volume-title":"Int. Joint Conf. on Neural Networks (IJCNN), 265--268","author":"Chester D.","year":"1990","unstructured":"Chester , D. 1990 . Why two hidden layers are better than one . In Int. Joint Conf. on Neural Networks (IJCNN), 265--268 . Chester, D. 1990. Why two hidden layers are better than one. In Int. Joint Conf. on Neural Networks (IJCNN), 265--268."},{"key":"e_1_2_2_4_1","unstructured":"Cohen M. F. Wallace J. and Hanrahan P. 1993. Radiosity and realistic image synthesis. Academic Press Professional Inc. San Diego CA USA.   Cohen M. F. Wallace J. and Hanrahan P. 1993. Radiosity and realistic image synthesis . Academic Press Professional Inc. San Diego CA USA."},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.02063.x"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1111411.1111428"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276453"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.77"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/PG.2007.38"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2006.41"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1111411.1111440"},{"key":"e_1_2_2_12_1","unstructured":"FAQ. How many hidden layers should I use? Neural Network FAQ Usenet newsgroup comp.ai.neural-nets ftp:\/\/ftp.sas.com\/pub\/neural\/FAQ3.html#A_hl.  FAQ. How many hidden layers should I use? Neural Network FAQ Usenet newsgroup comp.ai.neural-nets ftp:\/\/ftp.sas.com\/pub\/neural\/FAQ3.html#A_hl."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1111411.1111413"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280816"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.329697"},{"key":"e_1_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Hastie T. Tibshirani R. and Friedman J. 2009. The Elements of Statistical Learning: Data Mining Inference and Prediction 2 ed. Springer.  Hastie T. Tibshirani R. and Friedman J. 2009. The Elements of Statistical Learning: Data Mining Inference and Prediction 2 ed. Springer.","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141998"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/946250.946970"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(89)90049-0"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"e_1_2_2_21_1","volume-title":"Mitsuba renderer. Department of Computer Science","author":"Jakob W.","unstructured":"Jakob , W. , 2010. Mitsuba renderer. Department of Computer Science , Cornell University . (http:\/\/www.mitsuba-renderer.org). Jakob, W., 2010. Mitsuba renderer. Department of Computer Science, Cornell University. (http:\/\/www.mitsuba-renderer.org)."},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1730804.1730821"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258769"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/2383894.2383915"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073334"},{"key":"e_1_2_2_26_1","volume-title":"Proc. Compugraphics '93","author":"Lafortune E. P.","unstructured":"Lafortune , E. P. , and Willems , Y. D . 1993. Bi-directional path tracing . In Proc. Compugraphics '93 , 145--153. Lafortune, E. P., and Willems, Y. D. 1993. Bi-directional path tracing. In Proc. Compugraphics '93, 145--153."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360636"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/2383533.2383579"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1572769.1572783"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.2307\/1271432"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276469"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015749"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2009.97"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01364.x"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778803"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1561\/0600000021"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1409060.1409082"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.02093.x"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566612"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882281"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1944745.1944763"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141981"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2008.01313.x"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1138450.1138456"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/2383847.2383852"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531397"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/133994.134078"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2461912.2462009","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2461912.2462009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:48:39Z","timestamp":1750236519000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2461912.2462009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,7,21]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2013,7,21]]}},"alternative-id":["10.1145\/2461912.2462009"],"URL":"https:\/\/doi.org\/10.1145\/2461912.2462009","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,7,21]]},"assertion":[{"value":"2013-07-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}