Computer Graphics Forum最新文献

{"title":"Wavelet Representation and Sampling of Complex Luminaires","authors":"A. Atanasov,&nbsp;V. Koylazov","doi":"10.1111/cgf.70163","DOIUrl":"https://doi.org/10.1111/cgf.70163","url":null,"abstract":"<p>We contribute a technique for rendering the illumination of complex luminaires based on wavelet-compressed light fields while the direct appearance of the luminaire is handled with previous techniques. During a brief photon tracing phase, we pre-compute the radiance field of the luminaire. Then, we employ a compression scheme which is designed to facilitate fast per-ray run-time reconstructions of the field and importance sampling. To treat aliasing, we propose a two-component filtering solution: a 4D Gaussian filter during the pre-computation stage and a 4D stochastic Gaussian filter during rendering. We have developed an importance sampling strategy based on providing an initial guess from low-resolution and low-memory viewpoint samplers that is subsequently refined by a hierarchical process over the wavelet frequency bands. Our technique is straightforward to integrate in rendering systems and has all the features that make it practical for production renderers — MIS compatibility, brief pre-computation, low memory requirements, and efficient field evaluation and importance sampling.</p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 4","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144768035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A wave-optics BSDF for correlated scatterers","authors":"Ruomai Yang,&nbsp;Juhyeon Kim,&nbsp;Adithya Pediredla,&nbsp;Wojciech Jarosz","doi":"10.1111/cgf.70167","DOIUrl":"https://doi.org/10.1111/cgf.70167","url":null,"abstract":"<p>We present a wave-optics-based BSDF for simulating the corona effect observed when viewing strong light sources through materials such as certain fabrics or glass surfaces with condensation. These visual phenomena arise from the interference of diffraction patterns caused by correlated, disordered arrangements of droplets or pores. Our method leverages the pair correlation function (PCF) to decouple the spatial relationships between scatterers from the diffraction behavior of individual scatterers. This two-level decomposition allows us to derive a physically based BSDF that provides explicit control over both scatterer shape and spatial correlation. We also introduce a practical importance sampling strategy for integrating our BSDF within a Monte Carlo renderer. Our simulation results and real-world comparisons demonstrate that the method can reliably reproduce the characteristics of the corona effects in various real-world diffractive materials.</p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 4","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144767950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-Time Importance Deep Shadows Maps with Hardware Ray Tracing","authors":"René Kern,&nbsp;Felix Brüll,&nbsp;Thorsten Grosch","doi":"10.1111/cgf.70178","DOIUrl":"https://doi.org/10.1111/cgf.70178","url":null,"abstract":"<div>\u0000 <p>Rendering shadows for semi-transparent objects like smoke significantly enhances the realism of the final image. With advancements in ray tracing hardware, tracing visibility rays in real time has become possible. However, generating shadows for semi-transparent objects requires evaluating multiple or all intersections along the ray, resulting in a deep shadow ray. Deep Shadow Maps (DSM) offer an alternative but are constrained by their fixed resolution. We introduce Importance Deep Shadow Maps (IDSM), a real-time algorithm that adaptively distributes Deep Shadow samples based on importance captured from the current camera viewport. Additionally, we propose a novel DSM data structure built on the ray tracing acceleration structure, improving performance for scenarios requiring many samples per DSM texel. Our IDSM approach achieves speedups of up to <i>×6.89</i> compared to hardware ray tracing while maintaining a nearly indistinguishable quality level.</p>\u0000 </div>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 4","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.70178","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144767954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reshadable Impostors with Level-of-Detail for Real-Time Distant Objects Rendering","authors":"X. Wu,&nbsp;Z. Zeng,&nbsp;J. Zhu,&nbsp;L. Wang","doi":"10.1111/cgf.70183","DOIUrl":"https://doi.org/10.1111/cgf.70183","url":null,"abstract":"<p>We propose a new image-based representation for real-time distant objects rendering: Reshadable Impostors with Level-of-Detail (RiLoD). By storing compact geometric and material information captured from a few reference views, RiLoD enables reliable forward mapping to generate target views under dynamic lighting and edited material attributes. In addition, it supports seamless transitions across different levels of detail. To support reshading and LoD simultaneously while maintaining a minimal memory footprint and bandwidth requirement, our key design is a compact yet efficient representation that encodes and compresses the necessary material and geometric information in each reference view. To further improve the visual fidelity, we use a reliable forward mapping technique combined with a hole-filling filtering strategy to ensure geometric completeness and shading consistency. We demonstrate the practicality of RiLoD by integrating it into a modern real-time renderer. RiLoD delivers fast performance across a variety of test scenes, supports smooth transitions between levels of detail as the camera moves closer or farther, and avoids the typical artifacts of impostor techniques that result from neglecting the underlying geometry.</p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 4","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144768036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Front Matter","authors":"","doi":"10.1111/cgf.70143","DOIUrl":"https://doi.org/10.1111/cgf.70143","url":null,"abstract":"&lt;p&gt;EuroVis 2025, the Eurographics Conference on Visualization was held in Luxembourg City, Luxembourg from June 2 to 6, 2025.&lt;/p&gt;&lt;p&gt;Since its beginnings in 1990, EuroVis has evolved alongside the field it represents. What started as the &lt;i&gt;Eurographics Workshop on Visualization in Scientific Computing&lt;/i&gt; later became &lt;i&gt;VisSym&lt;/i&gt; from 1999 to 2005. In 2005, it took on the name we know today — &lt;i&gt;EuroVis,&lt;/i&gt; officially the &lt;i&gt;Eurographics / IEEE VGTC Conference on Visualization&lt;/i&gt; — a title that reflects its broad scope across data visualization.&lt;/p&gt;&lt;p&gt;Each year, EuroVis brings together researchers and practitioners exploring how we see and understand data — ranging from complex spatial forms like volumes and vector fields to abstract information such as graphs, texts, and high-dimensional data. The conference dives into theory, hardware acceleration, visual perception, interaction, user studies, and countless real-world applications. Though always hosted in Europe, EuroVis is a truly global event. The 2025 Full Papers International Program Committee (IPC) alone featured 88 experts from across Europe, North America, Asia, and the Middle East. The research, too, reflects this diversity — pushing the boundaries of visualization from all corners of the world.&lt;/p&gt;&lt;p&gt;The proceedings of EuroVis are freely accessible during the conference week, most of them are published open access. Full papers appear as a special issue of the Computer Graphics Forum journal. In 2025, EuroVis received 200 abstract submissions, leading to 167 full paper submissions. With the exception of one desk-rejected paper, all submissions underwent the full peer-review process. Notably, the number of submissions for EuroVis 2025 saw a significant 25% increase compared to 2024 — highlighting the growing momentum and interest in the visualization community.&lt;/p&gt;&lt;p&gt;In 2025, authors had the option to submit their papers anonymously, although members of the IPC could still view author identities within the submission system. The review process once again employed a structured review form, but no rebuttal phase was included. Each submission received four to five reviews in the first round — two from IPC members and two or three from external experts selected by them. Reviewers then engaged in an online discussion to assess the papers and provided a recommendation of conditional acceptance or rejection to the Full Papers Chairs. Based on these recommendations, the Chairs assigned one of three outcomes to each submission: conditional acceptance, recommendation for fast-track consideration in the journal Computer Graphics Forum, or rejection. A total of 46 papers received conditional acceptance and proceeded to a second review round after revisions by the authors. All 46 papers were ultimately accepted, resulting in a final acceptance rate of 27.5%. Additionally, five papers were invited to undergo revisions for potential publication through the &lt;i&gt;Computer Graphics Forum&lt;/i&gt; fast-track ","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 3","pages":"i-xix"},"PeriodicalIF":2.7,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.70143","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Front Matter","authors":"","doi":"10.1111/cgf.70153","DOIUrl":"https://doi.org/10.1111/cgf.70153","url":null,"abstract":"<p><b>STARs Chairs</b></p><p>Marco Angelini, Link Università di Roma</p><p>Christoph Garth, RPTU University Kaiserslautern-Landau</p><p>Andreas Kerren, Linköping University</p><p>Jürgen Bernard, University of Zurich, Switzerland</p><p>Lonni Besançon, Linköping University, Sweden</p><p>Chris Bryan, Arizona State University, United states</p><p>Paolo Buono, University of Bari Aldo Moro, Italia</p><p>Angelos Chatzimparmpas, Utrecht University, Nederlands</p><p>Hank Childs, University of Oregon, United states</p><p>Raimund Dachselt, TUD Dresden University of Technology, Germany</p><p>Sara Di Bartolomeo, TU Wien, Austria</p><p>Soumya Dutta, Indian Institute of Technology Kanpur (IIT Kanpur), India</p><p>Florian Heimerl, University of Wisconsin-Madison, United states</p><p>Christian Heine, Leipzig University, Germany</p><p>Takayuki Itoh, Ochanomizu University, Japan</p><p>Mike Kirby, University of Utah, United states</p><p>Stephen Kobourov, Technical University Munich, Germany</p><p>Jörn Kohlhammer, Fraunhofer IGD, Germany</p><p>Robert Krüger, New York University, United states</p><p>Robert Laramee, University of Nottingham, United Kingdom</p><p>Lars Linsen, University of Münster, Germany</p><p>Carolina Nobre, University of Toronto, Canada</p><p>Giuseppe Santucci, Sapienza University of Rome, Italia</p><p>Gerik Scheuermann, Leipzig University, Germany</p><p>Johanna Schmidt, VRVis GmbH, Austria</p><p>Tobias Schreck, Graz University of Technology, Austria</p><p>Thomas Schultz, University of Bonn, Germany</p><p>Alexandru Telea, Utrecht University, Nederlands</p><p>Pere-Pau Vázquez, Universitat Politècnica de Catalunya, Spain</p><p>Tatiana von Landesberger, University of Cologne, Germany</p><p>Daniel Wiegreffe, Leipzig University, Germany</p><p>Mutlu Belgin, Pro2Future GmbH, Austria</p><p>Darya Biparva, University of Minnesota, USA</p><p>Francisco Maria Calisto, Univeristy of Lisbon, Portugal</p><p>Alexandra Cortez Ordoñez, Universitat Politècnica de Catalunya, Spain</p><p>Emilio Di Giacomo, University of Perugia, Italy</p><p>Takanori Fujiwara, Linköping University, Sweden</p><p>Christina Gillmann, Fraunhofer FIT, Germany</p><p>Lace Padilla, Northeastern University, USA</p><p>Roy Ruddle, University of Leeds, UK</p><p>Sudhanshu Sane, NREL, USA</p><p>Andrea Schnorr, RPTU University Kaiserslautern-Landau, Germany</p><p>Mara Solen, University of British Columbia, Canada</p><p>Christian Tominski, University of Rostock, Germany</p><p>Ye Zhang, University Of Pittsburgh, USA</p><p>\u0000 </p><p>\u0000 </p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 3","pages":"i-v"},"PeriodicalIF":2.7,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.70153","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Front Matter","authors":"","doi":"10.1111/cgf.70090","DOIUrl":"https://doi.org/10.1111/cgf.70090","url":null,"abstract":"<p>The European Association for Computer Graphics 46^th Annual Conference</p><p>London, UK</p><p><b>STARs Co-Chairs</b></p><p>Yulia Gryaditskaya (Adobe Research, UK)</p><p>Pooran Memari (CNRS, LIX, Ecole Polytechnique, Inria, IP Paris, France)</p><p>Published by</p><p><i>The Eurographics Association and John Wiley &amp; Sons Ltd.</i> in Computer Graphics <i>forum,</i> Volume 44 (2025), Issue 2 ISSN 1467-8659</p><p>\u0000 </p><p>\u0000 </p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 2","pages":"i-iii"},"PeriodicalIF":2.7,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.70090","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144666153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Front Matter","authors":"","doi":"10.1111/cgf.70089","DOIUrl":"https://doi.org/10.1111/cgf.70089","url":null,"abstract":"&lt;p&gt;The European Association for Computer Graphics 46&lt;sup&gt;th&lt;/sup&gt; Annual Conference&lt;/p&gt;&lt;p&gt;London, UK&lt;/p&gt;&lt;p&gt;&lt;b&gt;Full Papers Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Angela Dai (Technical University of Munich, Germany)&lt;/p&gt;&lt;p&gt;Adrien Bousseau (INRIA, Université Côte d'Azur, France)&lt;/p&gt;&lt;p&gt;&lt;b&gt;Conference Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Niloy Mitra (University College London and Adobe Research, UK)&lt;/p&gt;&lt;p&gt;Tobias Ritschel (University College London, UK)&lt;/p&gt;&lt;p&gt;Published by&lt;/p&gt;&lt;p&gt;&lt;i&gt;The Eurographics Association and John Wiley &amp; Sons Ltd.&lt;/i&gt; in Computer Graphics &lt;i&gt;forum,&lt;/i&gt; Volume 44 (2025), Issue 2 ISSN 1467-8659&lt;/p&gt;&lt;p&gt;&lt;b&gt;STARs Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Yulia Gryaditskaya (Adobe Research, UK)&lt;/p&gt;&lt;p&gt;Pooran Memari (CNRS, LIX, Ecole Polytechnique, Inria, IP Paris, France)&lt;/p&gt;&lt;p&gt;&lt;b&gt;Tutorials Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Rafał Mantiuk (University of Cambridge, UK)&lt;/p&gt;&lt;p&gt;Klaus Hildebrandt (TU Delft, The Netherands)&lt;/p&gt;&lt;p&gt;&lt;b&gt;Short Papers Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Duygu Ceylan (Adobe Research, UK)&lt;/p&gt;&lt;p&gt;Tzu-Mao Li (University of California, San Diego, US)&lt;/p&gt;&lt;p&gt;&lt;b&gt;Education Papers Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Rafael Kuffner dos Anjos (University of Leeds, UK)&lt;/p&gt;&lt;p&gt;Karina Rodriguez Echavarria (University of Brighton, UK)&lt;/p&gt;&lt;p&gt;&lt;b&gt;Posters Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Tobias Günther (Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany)&lt;/p&gt;&lt;p&gt;Zahra Montazeri (University of Manchester, UK)&lt;/p&gt;&lt;p&gt;&lt;b&gt;Doctoral Consortium Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Lingjie Liu (University of Pennsylvania, US)&lt;/p&gt;&lt;p&gt;Gurprit Singh (MPI Informatik, Germany)&lt;/p&gt;&lt;p&gt;&lt;b&gt;Diversity Chairs&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Noura Faraj (Université de Montpellier, France)&lt;/p&gt;&lt;p&gt;&lt;b&gt;Sustainability&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Dennis Bukenberger (Technical University of Munich, Germany)&lt;/p&gt;&lt;p&gt;This issue of the Computer Graphics Forum contains the technical full papers program of the Eurographics Association 46th annual conference, held in London, England from 12-16 May 2025. The Eurographics annual venue presents a unique opportunity to present outstanding technical contributions in computer graphics. The full papers selected for publication in the Computer Graphics Forum journal are arguably the most prestigious feature of the conference.&lt;/p&gt;&lt;p&gt;The technical paper selection process involved a group of 98 experts forming the International Program Committee (IPC). We invited experts without more than two consecutive years of participation in the IPC so that the committee can be regularly renewed. The IPC members covered a diverse range of research subareas in computer graphics.&lt;/p&gt;&lt;p&gt;We received a total of 211 full submissions, six of which were desk-rejected because they were out of scope or because of plagiarism or double-submission issues. A sorting committee, consisting of the two Chairs and six sorting committee members, subsequently assigned each paper to two IPC members, as either primary or secondary reviewer, up to five papers, respecting to their preferences, expertise, conflicts, and automatically computed matching scores between IPC members and submitted papers. The primary and secondary reviewers in turn invited three addit","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 2","pages":"i-xxvii"},"PeriodicalIF":2.7,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.70089","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144666240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implicit UVs: Real-time semi-global parameterization of implicit surfaces","authors":"Baptiste Genest,&nbsp;Pierre Gueth,&nbsp;Jérémy Levallois,&nbsp;Stephanie Wang","doi":"10.1111/cgf.70056","DOIUrl":"https://doi.org/10.1111/cgf.70056","url":null,"abstract":"<p>Implicit representations of shapes are broadly used in computer graphics since they offer many valuable properties in design, modeling, and animation. However, their implicit and volumetric nature makes applying 2D textures fundamentally challenging. We propose a method to compute point-wise and parallelizable semi-global parameterizations of implicit surfaces for texturing, rendering, and modeling purposes. Our method not only defines local patches of parameterization, but also enables the merging of multiple adjacent patches into large and spatially coherent ones that conform to the geometry. Implemented in shaders into a sphere-tracing pipeline, our method allows users to edit the uv-fields with real-time visualization. We demonstrate how to add rendering details (texture, normal, displacement, etc.) using our parameterization, as well extending modeling tools with implicit shell maps. Furthermore, the textured objects remain implicit and can still be used in a modeling pipeline.</p>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 2","pages":""},"PeriodicalIF":2.7,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144666188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Data-Driven Approach to Analytical Dwivedi Guiding","authors":"Darryl Gouder,&nbsp;Jiří Vorba,&nbsp;Marc Droske,&nbsp;Alexander Wilkie","doi":"10.1111/cgf.70164","DOIUrl":"https://doi.org/10.1111/cgf.70164","url":null,"abstract":"<div>\u0000 <p>Path tracing remains the gold standard for high-fidelity subsurface scattering despite requiring numerous paths for noise-free estimates. We introduce a novel variance-reduction method based on two complementary zero-variance-theory-based approaches. The first one, analytical Dwivedi sampling, is lightweight but struggles with complex lighting. The second one, surface path guiding, learns incident illumination at boundaries to guide sampled paths, but it does not reduce variance from subsurface scattering. In our novel method, we enhance Dwivedi sampling by incorporating the radiance field learned only at the volume boundary. We use the average normal of points on an illuminated boundary region or directions sampled from distributions of incident light at the boundary as our analytical Dwivedi slab normals. Unlike previous methods based on Dwivedi sampling, our method is efficient even in scenes with complex light rigs typical for movie production and under indirect illumination. We achieve comparable noise reduction and even slightly improved estimates in some scenes compared to volume path guiding, and our method can be easily added on top of any existing surface path guiding system. Our method is particularly effective for homogeneous, isotropic media, bypassing the extensive training and caching inside the 3D volume that volume path guiding requires.</p>\u0000 </div>","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 4","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.70164","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144767964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}