{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:07:30Z","timestamp":1784268450625,"version":"3.55.0"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972194"],"award-info":[{"award-number":["61972194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032011"],"award-info":[{"award-number":["62032011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20211147"],"award-info":[{"award-number":["BK20211147"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2025,8,1]]},"abstract":"<jats:p>Contemporary path guiding employs an iterative training scheme to fit radiance distributions. However, existing methods combine the estimates generated in each iteration merely within image space, overlooking differences in the convergence of distribution fitting over individual light paths.<\/jats:p>\n                  <jats:p>\n                    This paper formulates the estimation combination task as a path reweighting process. To compute spatio-directional varying combination weights, we propose\n                    <jats:italic toggle=\"yes\">multiple importance reweighting<\/jats:italic>\n                    , leveraging the importance distributions from multiple guiding iterations. We demonstrate that our proposed path-level reweighting makes guiding algorithms less sensitive to noise and overfitting in distributions. This facilitates a finer subdivision of samples both spatially and temporally (i.e., over iterations), which leads to additional improvements in the accuracy of distributions and samples.\n                  <\/jats:p>\n                  <jats:p>Inspired by adaptive multiple importance sampling (AMIS), we introduce a simple yet effective mixture-based weighting scheme with theoretically guaranteed consistency, demonstrating good practical performance compared to alternative weighting schemes. To further foster usage with high sample rates, we introduce a hyperparameter that controls the size of sample storage. When this size limit is exceeded, low-valued samples are splatted during rendering and reweighted using a partial mixture of distributions. We found limiting the storage size reduces memory overhead and keeps variance reduction and bias comparable to the unlimited ones.<\/jats:p>\n                  <jats:p>Our method is largely agnostic to the underlying guiding method and compatible with conventional pixel reweighting techniques. Extensive evaluations underscore the feasibility of our approach in various scenes, achieving variance reduction with negligible bias over state-of-the-art solutions within equal sample rates and rendering time.<\/jats:p>","DOI":"10.1145\/3731144","type":"journal-article","created":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T04:02:22Z","timestamp":1753588942000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multiple Importance Reweighting for Path Guiding"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6620-1900","authenticated-orcid":false,"given":"Zhimin","family":"Fan","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6212-4224","authenticated-orcid":false,"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7673-718X","authenticated-orcid":false,"given":"Chenxi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9379-094X","authenticated-orcid":false,"given":"Ling-Qi","family":"Yan","sequence":"additional","affiliation":[{"name":"University of California Santa Barbara, Santa Barbara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7605-5206","authenticated-orcid":false,"given":"Yanwen","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4176-7617","authenticated-orcid":false,"given":"Jie","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-008-9059-x"},{"key":"e_1_2_2_2_1","volume-title":"Adaptive Multiple Importance Sampling. Scandinavian Journal of Statistics 39 (07","author":"Cornuet Jean-Marie","year":"2009","unstructured":"Jean-Marie Cornuet, Jean-Michel Marin, Antonietta Mira, and Christian Robert. 2009. Adaptive Multiple Importance Sampling. Scandinavian Journal of Statistics 39 (07 2009)."},{"key":"e_1_2_2_3_1","unstructured":"Mikhail Derevyannykh. 2022. Real-Time Path-Guiding Based on Parametric Mixture Models. (2022)."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14428"},{"key":"e_1_2_2_5_1","volume-title":"Neural Parametric Mixtures for Path Guiding. Conference Proceedings","author":"Dong Honghao","year":"2023","unstructured":"Honghao Dong, Guoping Wang, and Sheng Li. 2023. Neural Parametric Mixtures for Path Guiding. Conference Proceedings (2023)."},{"key":"e_1_2_2_6_1","volume-title":"Efficient Adaptive Multiple Importance Sampling. 2019 27th European Signal Processing Conference (EUSIPCO) (Sept.","author":"El-Laham Yousef","year":"2019","unstructured":"Yousef El-Laham, Luca Martino, Victor Elvira, and Monica F. Bugallo. 2019. Efficient Adaptive Multiple Importance Sampling. 2019 27th European Signal Processing Conference (EUSIPCO) (Sept. 2019), 1\u20135."},{"key":"e_1_2_2_7_1","article-title":"Advances in Importance Sampling. (Feb. 2021). Zhimin Fan, Pengpei Hong, Jie Guo, Changqing Zou, Yanwen Guo, and Ling-Qi Yan. 2023. Manifold Path Guiding for Importance Sampling Specular Chains","volume":"42","author":"Elvira V\u00edctor","year":"2021","unstructured":"V\u00edctor Elvira and Luca Martino. 2021. Advances in Importance Sampling. (Feb. 2021). Zhimin Fan, Pengpei Hong, Jie Guo, Changqing Zou, Yanwen Guo, and Ling-Qi Yan. 2023. Manifold Path Guiding for Importance Sampling Specular Chains. ACM Trans. Graph. 42, 6, Article 257 (dec 2023), 14 pages.","journal-title":"ACM Trans. Graph."},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658133"},{"key":"e_1_2_2_9_1","volume-title":"Path Tracing in Production. In ACM SIGGRAPH 2018 Courses","author":"Fascione Luca","year":"2018","unstructured":"Luca Fascione, Johannes Hanika, Rob Piek\u00e9, Ryusuke Villemin, Christophe Hery, Manuel Gamito, Luke Emrose, and Andr\u00e9 Mazzone. 2018. Path Tracing in Production. In ACM SIGGRAPH 2018 Courses (Vancouver, British Columbia, Canada) (SIGGRAPH '18). Association for Computing Machinery, Article 15, 79 pages."},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.142628"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356515"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530126"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2670473.2670496"},{"key":"e_1_2_2_14_1","unstructured":"Sebastian Herholz and Addis Dittebrandt. 2022. Intel\u00ae Open Path Guiding Library. http:\/\/www.openpgl.org."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3071773.3071781"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230635"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649310"},{"key":"e_1_2_2_18_1","unstructured":"Wenzel Jakob. 2010. Mitsuba renderer. http:\/\/www.mitsuba-renderer.org."},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"e_1_2_2_20_1","volume-title":"The Path Tracing Revolution in the Movie Industry. In ACM SIGGRAPH 2015 Courses","author":"Keller A.","unstructured":"A. Keller, L. Fascione, M. Fajardo, I. Georgiev, P. Christensen, J. Hanika, C. Eisenacher, and G. Nichols. 2015. The Path Tracing Revolution in the Movie Industry. In ACM SIGGRAPH 2015 Courses (Los Angeles, California) (SIGGRAPH '15). Association for Computing Machinery, New York, NY, USA, Article 24, 7 pages."},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323009"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658203"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.3150\/18-BEJ1042"},{"key":"e_1_2_2_24_1","first-page":"35","article-title":"Practical Path Guiding\" in Production. In ACM SIGGRAPH Courses: Path Guiding in Production, Chapter 10 (Los Angeles, California). ACM, New York","volume":"18","author":"M\u00fcller Thomas","year":"2019","unstructured":"Thomas M\u00fcller. 2019. \"Practical Path Guiding\" in Production. In ACM SIGGRAPH Courses: Path Guiding in Production, Chapter 10 (Los Angeles, California). ACM, New York, NY, USA, 18:35\u201318:48.","journal-title":"NY, USA"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13227"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341156"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392441"},{"key":"e_1_2_2_28_1","volume-title":"Focal Path Guiding for Light Transport Simulation. In ACM SIGGRAPH 2023 Conference Proceedings","author":"Rath Alexander","year":"2023","unstructured":"Alexander Rath, \u00d6mercan Yazici, and Philipp Slusallek. 2023. Focal Path Guiding for Light Transport Simulation. In ACM SIGGRAPH 2023 Conference Proceedings (Los Angeles, CA, USA) (SIGGRAPH '23). Association for Computing Machinery, New York, NY, USA, Article 30, 10 pages."},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275030"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392421"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14582"},{"key":"e_1_2_2_32_1","volume-title":"Final Gathering Using Adaptive Multiple Importance Sampling. In ACM SIGGRAPH ASIA 2010 Posters (SA '10)","author":"Tokuyoshi Yusuke","year":"2010","unstructured":"Yusuke Tokuyoshi, Shinji Ogaki, and Schoellhammer Sebastian. 2010. Final Gathering Using Adaptive Multiple Importance Sampling. In ACM SIGGRAPH ASIA 2010 Posters (SA '10). Association for Computing Machinery, New York, NY, USA, 1."},{"key":"e_1_2_2_33_1","unstructured":"Eric Veach. 1997. Robust Monte Carlo Methods for Light Transport Simulation."},{"key":"e_1_2_2_34_1","volume-title":"Bidirectional Estimators for Light Transport","author":"Veach Eric","unstructured":"Eric Veach and Leonidas Guibas. 1995a. Bidirectional Estimators for Light Transport. In Photorealistic Rendering Techniques, Georgios Sakas, Stefan M\u00fcller, and Peter Shirley (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 145\u2013167."},{"key":"e_1_2_2_35_1","volume-title":"Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '95)","author":"Veach Eric","unstructured":"Eric Veach and Leonidas J. Guibas. 1995b. Optimally Combining Sampling Techniques for Monte Carlo Rendering. In Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '95). Association for Computing Machinery, New York, NY, USA, 419\u2013428."},{"key":"e_1_2_2_36_1","volume-title":"Path Guiding in Production. In ACM SIGGRAPH 2019 Courses. ACM, Los Angeles California, 1\u201377","author":"Vorba Ji\u0159\u00ed","year":"2019","unstructured":"Ji\u0159\u00ed Vorba, Johannes Hanika, Sebastian Herholz, Thomas M\u00fcller, Jaroslav K\u0159iv\u00e5nek, and Alexander Keller. 2019. Path Guiding in Production. In ACM SIGGRAPH 2019 Courses. ACM, Los Angeles California, 1\u201377."},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601203"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392436"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13335"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:57:18Z","timestamp":1774634238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731144"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8,1]]}},"alternative-id":["10.1145\/3731144"],"URL":"https:\/\/doi.org\/10.1145\/3731144","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}