{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T08:17:06Z","timestamp":1783066626178,"version":"3.54.6"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["948846"],"award-info":[{"award-number":["948846"]}],"id":[{"id":"10.13039\/501100000781","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":[[2026,7,3]]},"abstract":"<jats:p>Discrete X-ray tomography reconstructs the internal structure of an object from X-ray projections, assuming that the volume is composed of a discrete set of known materials (e.g., steel, aluminum, and air). This is generally straightforward when many projections are available but becomes increasingly ill-posed as their number decreases. Discrete tomography has been extensively studied over the past five decades, resulting in a range of mature reconstruction algorithms.<\/jats:p>\n                  <jats:p>In this work, we introduce a new reconstruction method that draws inspiration from both classical computed tomography and recent advances in inverse rendering, demonstrating that a remarkably simple gradient-based inversion can significantly surpass the reconstruction quality of standard methods such as SIRT, DART, and TVR-DART. Our method represents each 3D location as a probability distribution over the set of known materials and minimizes a volumetric loss that encourages consistency with the measured projections. It supports nonlinear effects such as volumetric scattering and is simple to optimize and parallelize on compute accelerators.<\/jats:p>\n                  <jats:p>We evaluate our method on challenging 2D and 3D benchmarks, demonstrating superior performance particularly in sparse and limited-angle scenarios, where traditional techniques struggle with ambiguity.<\/jats:p>","DOI":"10.1145\/3811391","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:05:51Z","timestamp":1783062351000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Inverse Rendering for Discrete X-Ray Computed Tomography"],"prefix":"10.1145","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7470-3523","authenticated-orcid":false,"given":"Lovro","family":"Nuic","sequence":"first","affiliation":[{"name":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8449-4295","authenticated-orcid":false,"given":"Ziyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8151-8762","authenticated-orcid":false,"given":"Korbinian","family":"Sager","sequence":"additional","affiliation":[{"name":"Carl Zeiss AG, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6090-1121","authenticated-orcid":false,"given":"Wenzel","family":"Jakob","sequence":"additional","affiliation":[{"name":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Operator discretization library (ODL). Zenodo","author":"Adler Jonas","year":"2017","unstructured":"Jonas Adler, Holger Kohr, and Ozan \u00d6ktem. 2017. Operator discretization library (ODL). Zenodo (2017)."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_1_3_1","volume-title":"Information Geometry and Its Applications","unstructured":"Shun-ichi Amari. 2016. Information Geometry and Its Applications (1st ed.). Springer Publishing Company, Incorporated.","edition":"1"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/016173468400600107"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131661"},{"key":"e_1_2_1_6_1","volume-title":"Pattern recognition and machine learning","author":"Bishop Christopher M","unstructured":"Christopher M Bishop and Nasser M Nasrabadi. 2006. Pattern recognition and machine learning. Vol. 4. Springer."},{"key":"e_1_2_1_7_1","volume-title":"SDART: An algorithm for discrete tomography from noisy projections. Computer Vision and Image Understanding 129","author":"Bleichrodt F.","year":"2014","unstructured":"F. Bleichrodt, F. Tabak, and K.J. Batenburg. 2014. SDART: An algorithm for discrete tomography from noisy projections. Computer Vision and Image Understanding 129 (2014). Special section: Advances in Discrete Geometry for Computer Imagery."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1086\/149346"},{"key":"e_1_2_1_9_1","unstructured":"catchspider2002. 2023. svelte-svg-patterns: Create seamless patterns in SVG. https:\/\/github.com\/catchspider2002\/svelte-svg-patterns GitHub repository for SVG pattern generation."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.1713127"},{"key":"e_1_2_1_11_1","volume-title":"Kees Joost Batenburg, and Jan Sijbers","author":"Dabravolski Andrei","year":"2014","unstructured":"Andrei Dabravolski, Kees Joost Batenburg, and Jan Sijbers. 2014. A Multiresolution Approach to Discrete Tomography Using DART. PLOS ONE 9, 9 (09 2014), 1\u201310."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0927"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.1.000612"},{"key":"e_1_2_1_14_1","volume-title":"Jan De Beenhouwer, and Jan Sijbers","author":"Frenkel Daniel","year":"2023","unstructured":"Daniel Frenkel, Nathana\u00ebl Six, Jan De Beenhouwer, and Jan Sijbers. 2023. Tabu-DART: a dynamic update strategy for efficient discrete algebraic reconstruction. The Visual Computer 39, 10 (01 Oct 2023), 4671\u20134683."},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","unstructured":"R.J. Gardner P. Gritzmann and D. Prangenberg. 1999. On the computational complexity of reconstructing lattice sets from their X-rays. Discrete Mathematics 202 1 (1999).","DOI":"10.1016\/S0012-365X(98)00347-1"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10210-3_23"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_3"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-5193(72)90180-4"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508377"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185548"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3152632"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10921-022-00916-8"},{"key":"e_1_2_1_23_1","unstructured":"Wenzel Jakob S\u00e9bastien Speierer Nicolas Roussel Merlin Nimier-David Delio Vicini Tizian Zeltner Baptiste Nicolet Miguel Crespo Vincent Leroy and Ziyi Zhang. 2022b. Mitsuba 3 renderer. https:\/\/mitsuba-renderer.org."},{"key":"e_1_2_1_24_1","first-page":"4","article-title":"Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering","volume":"41","author":"Jakob Wenzel","year":"2022","unstructured":"Wenzel Jakob, S\u00e9bastien Speierer, Nicolas Roussel, and Delio Vicini. 2022a. Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering. Transactions on Graphics (Proceedings of SIGGRAPH) 41, 4 (July 2022).","journal-title":"Transactions on Graphics (Proceedings of SIGGRAPH)"},{"key":"e_1_2_1_25_1","unstructured":"Eric Jang Shixiang Gu and Ben Poole. 2017. Categorical Reparameterization with Gumbel-Softmax. arXiv:1611.01144 [stat.ML] https:\/\/arxiv.org\/abs\/1611.01144"},{"key":"e_1_2_1_26_1","unstructured":"Wojciech Jarosz. 2008. Efficient Monte Carlo Methods for Light Transport in Scattering Media. Ph. D. Dissertation. UC San Diego."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2021.100835"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_1_29_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2014). https:\/\/api.semanticscholar.org\/CorpusID:6628106"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2114894"},{"key":"e_1_2_1_32_1","volume-title":"Design and fabrication of 3D-printed patient-specific soft tissue and bone phantoms for CT imaging. Scientific reports 13, 1","author":"Mei Kai","year":"2023","unstructured":"Kai Mei, Pouyan Pasyar, Michael Geagan, Leening P Liu, Nadav Shapira, Grace J Gang, J Webster Stayman, and Peter B No\u00ebl. 2023. Design and fabrication of 3D-printed patient-specific soft tissue and bone phantoms for CT imaging. Scientific reports 13, 1 (2023), 17495."},{"key":"e_1_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul P. Srinivasan Matthew Tancik Jonathan T. Barron Ravi Ramamoorthi and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1399504.1360630"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480501"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459844"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/technologies12080139"},{"key":"e_1_2_1_38_1","unstructured":"Pattern Monster. 2023. Pattern Monster - SVG Pattern Generator. https:\/\/pattern.monster Online SVG pattern generator tool."},{"key":"e_1_2_1_39_1","volume-title":"Physically based rendering: From theory to implementation","author":"Pharr Matt","unstructured":"Matt Pharr, Wenzel Jakob, and Greg Humphreys. 2023. Physically based rendering: From theory to implementation. MIT Press."},{"key":"e_1_2_1_40_1","first-page":"262","article-title":"\u00dcber die Bestimmung von Funktionen durch ihre Integralwerte l\u00e4ngs gewisser Mannigfaltigkeiten","volume":"69","author":"Radon J.","year":"1917","unstructured":"J. Radon. 1917. \u00dcber die Bestimmung von Funktionen durch ihre Integralwerte l\u00e4ngs gewisser Mannigfaltigkeiten. Akad. Wiss. 69 (1917), 262\u2013277.","journal-title":"Akad. Wiss."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.68.9.2236"},{"key":"e_1_2_1_42_1","volume-title":"Statistical image reconstruction from limited projection data with intensity priors. Physics in Medicine & Biology 57, 7","author":"Rashed Essam A","year":"2012","unstructured":"Essam A Rashed and Hiroyuki Kudo. 2012. Statistical image reconstruction from limited projection data with intensity priors. Physics in Medicine & Biology 57, 7 (2012)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3030638.3030863"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530121"},{"key":"e_1_2_1_45_1","volume-title":"Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena 60, 1\u20134","author":"Rudin Leonid I","year":"1992","unstructured":"Leonid I Rudin, Stanley Osher, and Emad Fatemi. 1992. Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena 60, 1\u20134 (1992), 259\u2013268."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.1982.4307558"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.27.033670"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3125564"},{"key":"e_1_2_1_49_1","doi-asserted-by":"crossref","unstructured":"TM Sutton FB Brown FG Bischoff DB MacMillan CL Ellis JT Ward CT Ballinger DJ Kelly and L Schindler. 1999. The physical models and statistical procedures used in the RACER Monte Carlo code. Technical Report. Knolls Atomic Power Lab.(KAPL) Niskayuna NY (United States); Albany.","DOI":"10.2172\/767449"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2206042"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459804"},{"key":"e_1_2_1_52_1","volume-title":"X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction. arXiv preprint arXiv:2503.08596","author":"Wang Feiran","year":"2025","unstructured":"Feiran Wang, Jiachen Tao, Junyi Wu, Haoxuan Wang, Bin Duan, Kai Wang, Zongxin Yang, and Yan Yan. 2025. X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction. arXiv preprint arXiv:2503.08596 (2025)."},{"key":"e_1_2_1_53_1","unstructured":"Weiran Wang and Miguel \u00c1. Carreira-Perpi\u00f1\u00e1n. 2013. Projection onto the probability simplex: An efficient algorithm with a simple proof and an application. arXiv:1309.1541 [cs.LG]"},{"key":"e_1_2_1_54_1","volume-title":"An optimal radial profile order based on the Golden Ratio for time-resolved MRI","author":"Winkelmann Stefanie","year":"2006","unstructured":"Stefanie Winkelmann, Tobias Schaeffter, Thomas Koehler, Holger Eggers, and Olaf Doessel. 2006. An optimal radial profile order based on the Golden Ratio for time-resolved MRI. IEEE transactions on medical imaging 26, 1 (2006), 68\u201376."},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00197"},{"key":"e_1_2_1_56_1","volume-title":"Yuanhao Cai, Jiwen Cao, Yanhao Zhang, and Hongdong Li.","author":"Zha Ruyi","year":"2024","unstructured":"Ruyi Zha, Tao Jun Lin, Yuanhao Cai, Jiwen Cao, Yanhao Zhang, and Hongdong Li. 2024. R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_2_1_57_1","unstructured":"Ziyi Zhang Nicolas Roussel and Wenzel Jakob. 2024. Many-Worlds Inverse Rendering. arXiv:2408.16005 [cs.CV]"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730713"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2504869"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45886-1_21"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:34:24Z","timestamp":1783064064000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3811391"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,3]]}},"alternative-id":["10.1145\/3811391"],"URL":"https:\/\/doi.org\/10.1145\/3811391","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]},"assertion":[{"value":"2026-01-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}