{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T05:21:46Z","timestamp":1793856106466,"version":"4.6.1"},"reference-count":99,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006754","name":"United States Department of Defense | United States Army | U.S. Army Research, Development and Engineering Command | Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-20-2-0158"],"award-info":[{"award-number":["W911NF-20-2-0158"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"United States Department of Defense | United States Army | U.S. Army Research, Development and Engineering Command | Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-20-2-0158"],"award-info":[{"award-number":["W911NF-20-2-0158"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"United States Department of Defense | United States Army | U.S. Army Research, Development and Engineering Command | Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-20-2-0158"],"award-info":[{"award-number":["W911NF-20-2-0158"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"United States Department of Defense | United States Army | U.S. Army Research, Development and Engineering Command | Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-20-2-0158"],"award-info":[{"award-number":["W911NF-20-2-0158"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"United States Department of Defense | United States Army | U.S. Army Research, Development and Engineering Command | Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-20-2-0158"],"award-info":[{"award-number":["W911NF-20-2-0158"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CAREER"],"award-info":[{"award-number":["CAREER"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"United States Department of Defense | United States Army | U.S. Army Research, Development and Engineering Command | Army Research Office","doi-asserted-by":"publisher","award":["Young Investigator Program"],"award-info":[{"award-number":["Young Investigator Program"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-023-00662-0","type":"journal-article","created":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T12:02:47Z","timestamp":1685620967000},"page":"572-580","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["Incorporating physics into data-driven computer vision"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2444-2503","authenticated-orcid":false,"given":"Achuta","family":"Kadambi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Celso","family":"de Melo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cho-Jui","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mani","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Soatto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,1]]},"reference":[{"key":"662_CR1","doi-asserted-by":"crossref","unstructured":"Thapa, S., Li, N. & Ye, J. Dynamic fluid surface reconstruction using deep neural network. In: 2020 IEEE\/CVF Conf. Computer Vision and Pattern Recognition 21\u201330 (IEEE, 2020).","DOI":"10.1109\/CVPR42600.2020.00010"},{"key":"662_CR2","doi-asserted-by":"publisher","first-page":"656505","DOI":"10.3389\/fclim.2021.656505","volume":"3","author":"L Schweri","year":"2021","unstructured":"Schweri, L. et al. A physics-aware neural network approach for flow data reconstruction from satellite observations. Front. Clim. 3, 656505 (2021).","journal-title":"Front. Clim."},{"key":"662_CR3","doi-asserted-by":"publisher","first-page":"222","DOI":"10.3390\/electronics10030222","volume":"10","author":"B Zhao","year":"2021","unstructured":"Zhao, B., Huang, Y., Wei, H. & Hu, X. Ego-motion estimation using recurrent convolutional neural networks through optical flow learning. Electronics 10, 222 (2021).","journal-title":"Electronics"},{"key":"662_CR4","doi-asserted-by":"publisher","unstructured":"Zhou, W., Zhang, H., Yan, Z., Wang, W. & Lin, L. DecoupledPoseNet: cascade decoupled pose learning for unsupervised camera ego-motion estimation. IEEE Trans. Multimedia https:\/\/doi.org\/10.1109\/TMM.2022.3144958 (2022).","DOI":"10.1109\/TMM.2022.3144958"},{"key":"662_CR5","doi-asserted-by":"publisher","unstructured":"Li, W. et al. Dynamic registration: joint ego motion estimation and 3d moving object detection in dynamic environment. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2204.12769 (2022).","DOI":"10.48550\/arXiv.2204.12769"},{"key":"662_CR6","unstructured":"Frazzoli, E. Robust Hybrid Control for Autonomous Vehicle Motion Planning. PhD thesis, Massachusetts Institute of Technology (2001)."},{"key":"662_CR7","doi-asserted-by":"publisher","first-page":"116","DOI":"10.2514\/2.4856","volume":"25","author":"E Frazzoli","year":"2002","unstructured":"Frazzoli, E., Dahleh, M. A. & Feron, E. Real-time motion planning for agile autonomous vehicles. J. Guid. Control Dyn. 25, 116\u2013129 (2002).","journal-title":"J. Guid. Control Dyn."},{"key":"662_CR8","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s10846-009-9383-1","volume":"57","author":"C Goerzen","year":"2010","unstructured":"Goerzen, C., Kong, Z. & Mettler, B. A survey of motion planning algorithms from the perspective of autonomous UAV guidance. J. Intell. Rob. Syst. 57, 65\u2013100 (2010).","journal-title":"J. Intell. Rob. Syst."},{"key":"662_CR9","doi-asserted-by":"publisher","first-page":"367","DOI":"10.2307\/1418003","volume":"63","author":"JJ Gibson","year":"1950","unstructured":"Gibson, J. J. The perception of visual surfaces. Am. J. Psychol. 63, 367\u2013384 (1950).","journal-title":"Am. J. Psychol."},{"key":"662_CR10","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1109\/34.879802","volume":"22","author":"LJ Latecki","year":"2000","unstructured":"Latecki, L. J. & Lakamper, R. Shape similarity measure based on correspondence of visual parts. IEEE Trans. Pattern Anal. Mach. Intell. 22, 1185\u20131190 (2000).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"662_CR11","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0031-3203(01)00040-1","volume":"35","author":"F Mokhtarian","year":"2002","unstructured":"Mokhtarian, F. & Abbasi, S. Shape similarity retrieval under affine transforms. Pattern Recognit. 35, 31\u201341 (2002).","journal-title":"Pattern Recognit."},{"key":"662_CR12","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/BF03037590","volume":"18","author":"B Raytchev","year":"2000","unstructured":"Raytchev, B., Hasegawa, O. & Otsu, N. User-independent gesture recognition by relative-motion extraction and discriminant analysis. New Gener. Comput. 18, 117\u2013126 (2000).","journal-title":"New Gener. Comput."},{"key":"662_CR13","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1109\/TIP.2006.871114","volume":"15","author":"GA Atkinson","year":"2006","unstructured":"Atkinson, G. A. & Hancock, E. R. Recovery of surface orientation from diffuse polarization. IEEE Trans. Image Process. 15, 1653\u20131664 (2006).","journal-title":"IEEE Trans. Image Process."},{"key":"662_CR14","doi-asserted-by":"crossref","unstructured":"Ba, Y. et al. Deep shape from polarization. In: Proc. 16th Eur. Conf. Computer Vision 554\u2013571 (Springer, 2020).","DOI":"10.1007\/978-3-030-58586-0_33"},{"key":"662_CR15","doi-asserted-by":"crossref","unstructured":"Cao, Y. & Gu, Q. Generalization error bounds of gradient descent for learning over-parameterized deep ReLU networks. In: Proc. AAAI Conf. on Artificial Intelligence Vol. 34, 3349\u20133356 (AAAI, 2020).","DOI":"10.1609\/aaai.v34i04.5736"},{"key":"662_CR16","doi-asserted-by":"crossref","unstructured":"Rockwell, C., Johnson, J. & Fouhey, D. F. The 8-point algorithm as an inductive bias for relative pose prediction by ViTs. In: 2022 Int. Conf. 3D Vision (IEEE, 2022).","DOI":"10.1109\/3DV57658.2022.00028"},{"key":"662_CR17","unstructured":"Lu, Y., Lin, S., Chen, G. & Pan, J. ModLaNets: learning generalisable dynamics via modularity and physical inductive bias. In: Proc. 39th Int. Conf. Machine Learning (eds. Chaudhuri, K. et al.) Vol. 162, 14384\u201314397 (PMLR, 2022)."},{"key":"662_CR18","doi-asserted-by":"publisher","unstructured":"Achille, A. & Soatto, S. On the learnability of physical concepts: can a neural network understand what\u2019s real? Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2207.12186 (2022).","DOI":"10.48550\/ARXIV.2207.12186"},{"key":"662_CR19","doi-asserted-by":"publisher","unstructured":"Kilic, V. et al. Lidar Light Scattering Augmentation (LISA): physics-based simulation of adverse weather conditions for 3D object detection. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2107.07004 (2021).","DOI":"10.48550\/arXiv.2107.07004"},{"key":"662_CR20","unstructured":"Wang, C., Bentivegna, E., Zhou, W., Klein, L. & Elmegreen, B. Physics-informed neural network super resolution for advection-diffusion models. In: Annu. Conf. Neural Information Processing Systems (2020)."},{"key":"662_CR21","doi-asserted-by":"publisher","first-page":"107961","DOI":"10.1016\/j.ress.2021.107961","volume":"217","author":"MA Chao","year":"2022","unstructured":"Chao, M. A., Kulkarni, C., Goebel, K. & Fink, O. Fusing physics-based and deep learning models for prognostics. Reliab. Eng. Syst. Saf. 217, 107961 (2022).","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"662_CR22","unstructured":"Zhou, H., Greenwood, D., Taylor, S. Self-supervised monocular depth estimation with internal feature fusion. In: British Machine Vision Conf. 2021 (2021)."},{"key":"662_CR23","doi-asserted-by":"crossref","unstructured":"Klingner, M., Term\u00f6hlen, J.-A., Mikolajczyk, J. & Fingscheidt, T. Self-supervised monocular depth estimation: solving the dynamic object problem by semantic guidance. In: Proc. 16th Eur. Conf. Computer Vision 582\u2013600 (Springer, 2020).","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"662_CR24","doi-asserted-by":"crossref","unstructured":"Liu, L., Song, X., Wang, M., Liu, Y. & Zhang, L. Self-supervised monocular depth estimation for all day images using domain separation. In: Proc. IEEE\/CVF Int. Conf. on Computer Vision 12737\u201312746 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.01250"},{"key":"662_CR25","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A. & Gaidon, A. 3D packing for self-supervised monocular depth estimation. In: Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition 2485\u20132494 (IEEE, 2020).","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"662_CR26","doi-asserted-by":"crossref","unstructured":"Schwarz, M. & Behnke, S. Stillleben: realistic scene synthesis for deep learning in robotics. In: 2020 IEEE Int. Conf. Robotics and Automation 10502\u201310508 (IEEE, 2020).","DOI":"10.1109\/ICRA40945.2020.9197309"},{"key":"662_CR27","unstructured":"Lerer, A., Gross, S. & Fergus, R. Learning physical intuition of block towers by example. In: Proc. 33rd Int. Conf. on Machine Learning 430\u2013438 (2016)."},{"key":"662_CR28","unstructured":"Wu, J., Yildirim, I., Lim, J. J., Freeman, B. & Tenenbaum, J. Galileo: perceiving physical object properties by integrating a physics engine with deep learning. In: Adv. Neural Information Processing Systems Vol. 28 (2015)."},{"key":"662_CR29","doi-asserted-by":"crossref","unstructured":"Narang, Y., Sundaralingam, B., Macklin, M., Mousavian, A. & Fox, D. Sim-to-real for robotic tactile sensing via physics-based simulation and learned latent projections. In: 2021 IEEE Int. Conf. Robotics and Automation 6444\u20136451 (IEEE, 2021).","DOI":"10.1109\/ICRA48506.2021.9561969"},{"key":"662_CR30","doi-asserted-by":"publisher","first-page":"6274","DOI":"10.1109\/LRA.2022.3158725","volume":"7","author":"I Huang","year":"2022","unstructured":"Huang, I. et al. DefGraspSim: physics-based simulation of grasp outcomes for 3D deformable objects. IEEE Rob. Autom. Lett. 7, 6274\u20136281 (2022).","journal-title":"IEEE Rob. Autom. Lett."},{"key":"662_CR31","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.tics.2021.11.008","volume":"26","author":"CM de Melo","year":"2022","unstructured":"de Melo, C. M. et al. Next-generation deep learning based on simulators and synthetic data. Trends Cognit. Sci. 26, 174\u2013187 (2022).","journal-title":"Trends Cognit. Sci."},{"key":"662_CR32","doi-asserted-by":"publisher","first-page":"041001","DOI":"10.1088\/2632-2153\/ac9215","volume":"3","author":"B Jalali","year":"2022","unstructured":"Jalali, B., Zhou, Y., Kadambi, A. & Roychowdhury, V. Physics-AI symbiosis. Mach. Learn. Sci. Technol. 3, 041001 (2022).","journal-title":"Mach. Learn. Sci. Technol."},{"key":"662_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, S., Jakob, W. & Li, T.-M. Physics-based differentiable rendering: from theory to implementation. In: ACM SIGGRAPH 2020 (Association for Computing Machinery, 2020).","DOI":"10.1145\/3388769.3407454"},{"key":"662_CR34","doi-asserted-by":"publisher","unstructured":"Baek, S.-H. et al. Image-based acquisition and modeling of polarimetric reflectance. ACM Trans. Graph. https:\/\/doi.org\/10.1145\/3386569.3392387 (2020).","DOI":"10.1145\/3386569.3392387"},{"key":"662_CR35","doi-asserted-by":"crossref","unstructured":"Kondo, Y., Ono, T., Sun, L., Hirasawa, Y. & Murayama, J. Accurate polarimetric brdf for real polarization scene rendering. In: Eur. Conf. Computer Vision 2020 (eds. Vedaldi, A. et al.) 220\u2013236 (Springer, 2020).","DOI":"10.1007\/978-3-030-58529-7_14"},{"key":"662_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, K., Luan, F., Wang, Q., Bala, K. & Snavely, N. PhySG: inverse rendering with spherical Gaussians for physics-based material editing and relighting. In: IEEE\/CVF Conf. Computer Vision and Pattern Recognition (IEEE, 2021).","DOI":"10.1109\/CVPR46437.2021.00541"},{"key":"662_CR37","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y. & Vig, E. VirtualWorlds as proxy for multi-object tracking analysis. In: 2016 IEEE Conf. Computer Vision and Pattern Recognition 4340\u20134349 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.470"},{"key":"662_CR38","doi-asserted-by":"crossref","unstructured":"Ros, G., Sellart, L., Materzynska, J., Vazquez, D. & Lopez, A.M. The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. In: 2016 IEEE Conf. Computer Vision and Pattern Recognition 3234\u20133243 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.352"},{"key":"662_CR39","doi-asserted-by":"crossref","unstructured":"Prakash, A. et al. Structured domain randomization: bridging the reality gap by context-aware synthetic data. In: 2019 Int. Conf. Robotics and Automation 7249\u20137255 (IEEE, 2019).","DOI":"10.1109\/ICRA.2019.8794443"},{"key":"662_CR40","doi-asserted-by":"publisher","first-page":"902","DOI":"10.1007\/s11263-018-1073-7","volume":"126","author":"M M\u00fcller","year":"2018","unstructured":"M\u00fcller, M., Casser, V., Lahoud, J., Smith, N. & Ghanem, B. Sim4CV: a photo-realistic simulator for computer vision applications. Int. J. Comput. Vision 126, 902\u2013919 (2018).","journal-title":"Int. J. Comput. Vision"},{"key":"662_CR41","doi-asserted-by":"crossref","unstructured":"Richter, S. R., Vineet, V., Roth, S. & Koltun, V. Playing for data: ground truth from computer games. In: Eur. Conf. Computer Vision 2016 (eds. Leibe, B. et al.) 102\u2013118 (Springer, 2016).","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"662_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Z. et al. Synthetic generation of face videos with plethysmograph physiology. In: Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition 20587\u201320596 (2022).","DOI":"10.1109\/CVPR52688.2022.01993"},{"key":"662_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Jiang, C., Zhao, Y., Terzopoulos, D. & Zhu, S.-C. Inferring forces and learning human utilities from videos. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition 3823\u20133833 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.415"},{"key":"662_CR44","doi-asserted-by":"crossref","unstructured":"Chen, C. et al. SoundSpaces: audio-visual navigation in 3D environments. In: Proc. 16th Eur. Conf. Computer Vision 17\u201336 (Springer, 2020).","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"662_CR45","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1109\/TPAMI.2019.2899570","volume":"42","author":"W Luo","year":"2019","unstructured":"Luo, W. et al. End-to-end active object tracking and its real-world deployment via reinforcement learning. IEEE Trans. Pattern Anal. Mach. Intell. 42, 1317\u20131332 (2019).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"662_CR46","doi-asserted-by":"crossref","unstructured":"Tobin, J. et al. Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ Int. Conf. Intelligent Robots and Systems 23\u201330 (IEEE, 2017).","DOI":"10.1109\/IROS.2017.8202133"},{"key":"662_CR47","doi-asserted-by":"crossref","unstructured":"Sadeghi, F. & Levine, S. CAD2RL: real single-image flight without a single real image. In: Robotics: Science and Systems XIII (eds. Amato, N. M. et al.) (Massachusetts Institute of Technology, 2017).","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"662_CR48","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1109\/TRO.2020.2988642","volume":"36","author":"A Zeng","year":"2020","unstructured":"Zeng, A., Song, S., Lee, J., Rodriguez, A. & Funkhouser, T. TossingBot: learning to throw arbitrary objects with residual physics. Trans. Rob. 36, 1307\u20131319 (2020).","journal-title":"Trans. Rob."},{"key":"662_CR49","doi-asserted-by":"crossref","unstructured":"Ajay, A. et al. Augmenting physical simulators with stochastic neural networks: case study of planar pushing and bouncing. In: IROS 2018 (2018).","DOI":"10.1109\/IROS.2018.8593995"},{"key":"662_CR50","doi-asserted-by":"publisher","unstructured":"Kloss, A., Schaal, S. & Bohg, J. Combining learned and analytical models for predicting action effects from sensory data. Int. J. Rob. Res. https:\/\/doi.org\/10.1177\/0278364920954896 (2020).","DOI":"10.1177\/0278364920954896"},{"key":"662_CR51","doi-asserted-by":"crossref","unstructured":"Kadambi, A., Taamazyan, V., Shi, B. & Raskar, R. Polarized 3D: high-quality depth sensing with polarization cues. In: Proc. IEEE Int. Conf. Computer Vision 3370\u20133378 (IEEE, 2015).","DOI":"10.1109\/ICCV.2015.385"},{"key":"662_CR52","doi-asserted-by":"crossref","unstructured":"Kalra, A. et al. Deep polarization cues for transparent object segmentation. In: 2020 IEEE\/CVF Conf. Computer Vision and Pattern Recognition 8599\u20138608 (IEEE, 2020).","DOI":"10.1109\/CVPR42600.2020.00863"},{"key":"662_CR53","doi-asserted-by":"crossref","unstructured":"Zou, S. et al. 3D human shape reconstruction from a polarization image. In: Proc. 16th Eur. Conf. Computer Vision 351\u2013368 (Springer, 2020).","DOI":"10.1007\/978-3-030-58568-6_21"},{"key":"662_CR54","unstructured":"Seo, S. et al. Controlling neural networks with rule representations. In: Adv. Neural Information Processing Systems (2021)."},{"key":"662_CR55","doi-asserted-by":"crossref","unstructured":"Klinghoffer, T., Somasundaram, S., Tiwary, K. & Raskar, R. Physics vs. learned priors: Rethinking camera and algorithm design for task-specific imaging. In 2022 IEEE International Conference on Computational Photography (ICCP) 1\u201312 (IEEE, 2022).","DOI":"10.1109\/ICCP54855.2022.9887681"},{"key":"662_CR56","unstructured":"Janner, M., Wu, J., Kulkarni, T. D., Yildirim, I. & Tenenbaum, J. B. Self-supervised intrinsic image decomposition. In: Proc. 31st Int. Conf. Neural Information Processing Systems 5938\u20135948 (Curran Associates, 2017)."},{"key":"662_CR57","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1190\/INT-2018-0230.1","volume":"7","author":"J Vamaraju","year":"2019","unstructured":"Vamaraju, J. & Sen, M. K. Unsupervised physics-based neural networks for seismic migration. Interpretation 7, 189\u2013200 (2019).","journal-title":"Interpretation"},{"key":"662_CR58","doi-asserted-by":"crossref","unstructured":"Rupe, A. et al. DisCo: physics-based unsupervised discovery of coherent structures in spatiotemporal systems. In: 2019 IEEE\/ACM Workshop on Machine Learning in High Performance Computing Environments 75\u201387 (IEEE, 2019).","DOI":"10.1109\/MLHPC49564.2019.00013"},{"key":"662_CR59","doi-asserted-by":"crossref","unstructured":"Hui, Z., Chakrabarti, A., Sunkavalli, K. & Sankaranarayanan, A. C. Learning to separate multiple illuminants in a single image. In: Computer Vision and Pattern Recognition 2019 (2019).","DOI":"10.1109\/CVPR.2019.00390"},{"key":"662_CR60","doi-asserted-by":"crossref","unstructured":"Nestmeyer, T., Lalonde, J., Matthews, I. & Lehrmann, A. Learning physics-guided face relighting under directional light. In: 2020 IEEE\/CVF Conf. Computer Vision and Pattern Recognition 5123\u20135132 (IEEE, 2020).","DOI":"10.1109\/CVPR42600.2020.00517"},{"key":"662_CR61","unstructured":"Alotaibi, S. & Smith, W. A. P. BioFaceNet: deep biophysical face image interpretation. In: Proc. British Machine Vision Conf. (2019)."},{"key":"662_CR62","doi-asserted-by":"crossref","unstructured":"Cai, G., Yan, K., Dong, Z., Gkioulekas, I. & Zhao, S. Physics\u2010based inverse rendering using combined implicit and explicit geometries. Comput. Graph. Forum 41, 129\u2013138 (2022).","DOI":"10.1111\/cgf.14592"},{"key":"662_CR63","doi-asserted-by":"crossref","unstructured":"Halder, S. S., Lalonde, J.-F. & de Charette, R. Physics-based rendering for improving robustness to rain. In: Proc. IEEE\/CVF Int. Conf. Computer Vision 10203\u201310212 (IEEE, 2019).","DOI":"10.1109\/ICCV.2019.01030"},{"key":"662_CR64","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Man, T. & Yuan, W. Simulation of vision-based tactile sensors using physics based rendering. In: 2021 IEEE Int. Conf. Robotics and Automation 1\u20137 (IEEE, 2021).","DOI":"10.1109\/ICRA48506.2021.9561122"},{"key":"662_CR65","doi-asserted-by":"crossref","unstructured":"Tewari, A. et al. Advances in neural rendering. In: Computer Graphics Forum Vol. 41, 703\u2013735 (Wiley, 2022).","DOI":"10.1111\/cgf.14507"},{"key":"662_CR66","doi-asserted-by":"crossref","unstructured":"Nayar, S. K. & Narasimhan, S. G. Vision in bad weather. In: Proc. 7th IEEE Int. Conf. Computer Vision Vol. 2, 820\u20138272 (1999).","DOI":"10.1109\/ICCV.1999.790306"},{"key":"662_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, H. & Patel, V. M. Densely connected pyramid dehazing network. In: 2018 IEEE\/CVF Conf. Computer Vision and Pattern Recognition 3194\u20133203 (2018).","DOI":"10.1109\/CVPR.2018.00337"},{"key":"662_CR68","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, Y., Yang, Y. & Liu, D. PSD: principled synthetic-to-real dehazing guided by physical priors. In: 2021 IEEE\/CVF Conf. Computer Vision and Pattern Recognition 7176\u20137185 (2021).","DOI":"10.1109\/CVPR46437.2021.00710"},{"key":"662_CR69","doi-asserted-by":"crossref","unstructured":"Le, H., Vicente, T. F. Y., Nguyen, V., Hoai, M. & Samaras, D. A+D Net: training a shadow detector with adversarial shadow attenuation. In: Proc. Eur. Conf. Computer Vision (2018).","DOI":"10.1007\/978-3-030-01216-8_41"},{"key":"662_CR70","doi-asserted-by":"crossref","unstructured":"Jin, Y., Sharma, A. & Tan, R. T. DC-ShadowNet: single-image hard and soft shadow removal using unsupervised domain-classifier guided network. In: 2021 IEEE\/CVF Int. Conf. Computer Vision 5007\u20135016 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00498"},{"key":"662_CR71","doi-asserted-by":"crossref","unstructured":"Bogo, F. et al. Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: 14th Eur. Conf. Computer Vision 561\u2013578 (Springer, 2016).","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"662_CR72","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417877","volume":"39","author":"S Shimada","year":"2020","unstructured":"Shimada, S., Golyanik, V., Xu, W. & Theobalt, C. PhysCap: physically plausible monocular 3D motion capture in real time. ACM Trans. Graph. 39, 1\u201316 (2020).","journal-title":"ACM Trans. Graph."},{"key":"662_CR73","doi-asserted-by":"crossref","unstructured":"Shi, L. et al. A novel loss function incorporating imaging acquisition physics for pet attenuation map generation using deep learning. In: Medical Image Computing and Computer Assisted Intervention 2019 (eds. Shen, D. et al.) 723\u2013731. (Springer, 2019).","DOI":"10.1007\/978-3-030-32251-9_79"},{"key":"662_CR74","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1364\/OPTICA.391291","volume":"7","author":"CA Metzler","year":"2020","unstructured":"Metzler, C. A. et al. Deep-inverse correlography: towards real-time high-resolution non-line-of-sight imaging: erratum. Optica 7, 249\u2013251 (2020).","journal-title":"Optica"},{"key":"662_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, F. et al. Physics-based iterative projection complex neural network for phase retrieval in lensless microscopy imaging. In: 2021 IEEE\/CVF Conf. Computer Vision and Pattern Recognition 10518\u201310526 (IEEE, 2021).","DOI":"10.1109\/CVPR46437.2021.01038"},{"key":"662_CR76","unstructured":"Huang, L., Chen, H., Liu, T. & Ozcan, A. GedankenNet: self-supervised learning of hologram reconstruction using physics consistency. Preprint at https:\/\/arxiv.org\/abs\/2209.08288 (2022)."},{"key":"662_CR77","doi-asserted-by":"crossref","unstructured":"Bai, B. et al. Deep learning-enabled virtual histological staining of biological samples. Light Sci. Appl. 12, 57 (2023).","DOI":"10.1038\/s41377-023-01104-7"},{"key":"662_CR78","doi-asserted-by":"crossref","unstructured":"Kadambi, A. Achieving fairness in medical devices. Science 372, 30\u201331 (2021).","DOI":"10.1126\/science.abe9195"},{"key":"662_CR79","unstructured":"Zhao, E. Q. et al. Making thermal imaging more equitable and accurate: resolving solar loading biases. Preprint at https:\/\/arxiv.org\/abs\/2304.08832 (2023)."},{"key":"662_CR80","doi-asserted-by":"crossref","unstructured":"Vilesov, A. et al. Blending camera and 77 GHz radar sensing for equitable robust plethysmography. ACM Trans. Grap. 41, 1\u201314 (2022).","DOI":"10.1145\/3528223.3530161"},{"key":"662_CR81","doi-asserted-by":"publisher","unstructured":"Trager, M. et al. Linear spaces of meanings: the compositional language of vision-language models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2302.14383 (2023).","DOI":"10.48550\/arXiv.2302.14383"},{"key":"662_CR82","unstructured":"Fragkiadaki, K., Agrawal, P., Levine, S. & Malik, J. Learning visual predictive models of physics for playing billiards. In 4th International Conference on Learning Representations (ICLR, 2016)"},{"key":"662_CR83","doi-asserted-by":"crossref","unstructured":"Pradyumna, C. et al. On learning mechanical laws of motion from video using neural networks. IEEE Access 11 30129\u201330145 (2013).","DOI":"10.1109\/ACCESS.2023.3260405"},{"key":"662_CR84","first-page":"9180","volume":"33","author":"Y Li","year":"2020","unstructured":"Li, Y., Torralba, A., Anandkumar, A., Fox, D. & Garg, A. Causal discovery in physical systems from videos. Adv. Neural Inf. Process. Syst. 33, 9180\u20139192 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"662_CR85","unstructured":"Li, Y. et al. Visual grounding of learned physical models. In: Int. Conf. Machine Learning (2020)."},{"key":"662_CR86","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1038\/s43588-022-00281-6","volume":"2","author":"B Chen","year":"2022","unstructured":"Chen, B. et al. Automated discovery of fundamental variables hidden in experimental data. Nat. Comput. Sci. 2, 433\u2013442 (2022).","journal-title":"Nat. Comput. Sci."},{"key":"662_CR87","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","volume":"95","author":"D Hassabis","year":"2017","unstructured":"Hassabis, D., Kumaran, D., Summerfield, C. & Botvinick, M. Neuroscience-Inspired artificial intelligence. Neuron 95, 245\u2013258 (2017).","journal-title":"Neuron"},{"key":"662_CR88","doi-asserted-by":"crossref","unstructured":"Marblestone, A. H., Wayne, G. & Kording, K. P. Toward an integration of deep learning and neuroscience. Front. Comput. Neurosci. 10, 94 (2016).","DOI":"10.3389\/fncom.2016.00094"},{"key":"662_CR89","doi-asserted-by":"publisher","unstructured":"Bengio, Y., Lee, D.-H., Bornschein, J., Mesnard, T. & Lin, Z. Towards biologically plausible deep learning. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1502.04156 (2015).","DOI":"10.48550\/arXiv.1502.04156"},{"key":"662_CR90","doi-asserted-by":"publisher","first-page":"18327","DOI":"10.1073\/pnas.1306572110","volume":"110","author":"PW Battaglia","year":"2013","unstructured":"Battaglia, P. W., Hamrick, J. B. & Tenenbaum, J. B. Simulation as an engine of physical scene understanding. Proc. Natl Acad. Sci. USA 110, 18327\u201318332 (2013).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"662_CR91","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1111\/j.1467-7687.2007.00569.x","volume":"10","author":"ES Spelke","year":"2007","unstructured":"Spelke, E. S. & Kinzler, K. D. Core knowledge. Dev. Sci. 10, 89\u201396 (2007).","journal-title":"Dev. Sci."},{"key":"662_CR92","doi-asserted-by":"crossref","unstructured":"Wu, J., Lim, J. J., Zhang, H. & Tenenbaum, J. B. Physics 101: learning physical object properties from unlabeled videos. In: Proc. British Machine Vision Conference (2016).","DOI":"10.5244\/C.30.39"},{"key":"662_CR93","unstructured":"Bear, D. M. et al. Learning physical graph representations from visual scenes. In: Proc. 34th Int. Conf. Neural Information Processing Systems (2020)."},{"key":"662_CR94","unstructured":"GPT-4 Technical Report (OpenAI, 2023); https:\/\/cdn.openai.com\/papers\/gpt-4.pdf"},{"key":"662_CR95","first-page":"149","volume":"7","author":"G Chrupala","year":"2021","unstructured":"Chrupala, G., Alishahi, A. & Berg-Kirkpatrick, T. The science of language modeling. Annu. Rev. Ling. 7, 149\u2013176 (2021).","journal-title":"Annu. Rev. Ling."},{"key":"662_CR96","doi-asserted-by":"publisher","first-page":"2449","DOI":"10.1109\/TPAMI.2020.2969348","volume":"43","author":"J Pan","year":"2020","unstructured":"Pan, J. et al. Physics-based generative adversarial models for image restoration and beyond. IEEE Trans. Pattern Anal. Mach. Intell. 43, 2449\u20132462 (2020).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"662_CR97","doi-asserted-by":"crossref","unstructured":"Ba, Y. et al. Not just streaks: towards ground truth for single image deraining. In: Proc. 17th Eur. Conf. Computer Vision 723\u2013740 (Springer, 2022).","DOI":"10.1007\/978-3-031-20071-7_42"},{"key":"662_CR98","unstructured":"Bear, D. et al. Physion: evaluating physical prediction from vision in humans and machines. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1 (NeurIPS, 2021)."},{"key":"662_CR99","doi-asserted-by":"publisher","unstructured":"Ba, Y., Zhao, G. & Kadambi, A. Blending diverse physical priors with neural networks. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1910.00201 (2019).","DOI":"10.48550\/arXiv.1910.00201"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00662-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00662-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00662-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T19:13:12Z","timestamp":1687374792000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00662-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":99,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["662"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00662-0","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]},"assertion":[{"value":"30 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A.K. is an employee, receives salary and owns stock in Intrinsic (an Alphabet company); and is a co-founder and owns stock in Vayu Robotics. C.d.M. declares no competing interests. C.-J.H., M.S. and S.S. hold employment, draw salary from and hold stock in Amazon.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}