{"type":"ScholarlyArticle","title":"Efficient Multi-View Inverse Rendering Using a Hybrid Differentiable Rendering Method","authors":[{"name":"Xiangyang Zhu","slug":"xiangyang-zhu","given":"Xiangyang","family":"Zhu","affiliation":"School of Software , Tsinghua University , China; Beijing National Research Center for Information Science and Technology (BNRist) , China"},{"name":"Yiling Pan","slug":"yiling-pan","given":"Yiling","family":"Pan","affiliation":"School of Software , Tsinghua University , China; Beijing National Research Center for Information Science and Technology (BNRist) , China"},{"name":"Bailin Deng","slug":"bailin-deng","given":"Bailin","family":"Deng","affiliation":"School of Computer Science and Informatics , Cardiff University , UK"},{"name":"Bin Wang","slug":"bin-wang","given":"Bin","family":"Wang","affiliation":"School of Software , Tsinghua University , China; Beijing National Research Center for Information Science and Technology (BNRist) , China"}],"abstract":"Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently reconstruct the 3D geometry and reflectance of a scene from multi-view images captured by conventional hand-held cameras. Our method follows an analysis-by-synthesis approach and consists of two phases. In the initialization phase, we use traditional SfM and MVS methods to reconstruct a virtual scene roughly matching the real scene. Then in the optimization phase, we adopt a hybrid approach to refine the geometry and reflectance, where the geometry is first optimized using an approximate differentiable rendering method, and the reflectance is optimized afterward using a physically-based differentiable rendering method. Our hybrid approach combines the efficiency of approximate methods with the high-quality results of physically-based methods. Extensive experiments on synthetic and real data demonstrate that our method can produce reconstructions with similar or higher quality than state-of-the-art methods while being more efficient.","doi":"10.24963/ijcai.2023/205","url":"https://ijcai.org/proceedings/2023/205","pdf":"https://ijcai.org/proceedings/2023/0205.pdf","markdown":"https://ijcai.org/proceedings/2023/205.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/205","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Computer Vision","track":"Main Track","number":205,"pages":{"first":1849,"last":1857},"keywords":["Computer Vision: CV: Applications","Computer Vision: CV: 3D computer vision"],"videos":[],"references":[{"position":1,"raw":"[Aanæs et al., 2016] Henrik Aanæs, Rasmus Ramsbøl Jensen, George Vogiatzis, and et al. Large-scale data for multiple- view stereopsis. International Journal of Computer Vision, 120(2):153-168, 2016.","title":"Henrik Aanæs, Rasmus Ramsbøl Jensen, George Vogiatzis","authors":"Aanæs","year":"2016","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Aittala et al., 2016] Miika Aittala, Timo Aila, and Jaakko Lehtinen. Reflectance modeling by neural texture synthesis. ACM Trans. Graph. (TOG), 35(4):1-13, 2016.","title":"Reflectance modeling by neural texture synthesis","authors":"Miika Aittala, Timo Aila, Jaakko Lehtinen","year":"2016","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Boss et al., 2021] Mark Boss, Raphael Braun, Varun Jam- pani, and et al. Nerd: Neural reflectance decomposition from image collections. In Proceedings of the IEEE/CVF ICCV, pages 12684-12694, 2021.","title":"Nerd: Neural reflectance decomposition from image collections","authors":"Mark Boss, Raphael Braun, Varun Jampani","year":"2021","venue":"Proceedings of the IEEE/CVF ICCV","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2014] Guojun Chen, Yue Dong, Pieter Peers, and et al. Reflectance scanning: Estimating shading frame and brdf with generalized linear light sources. ACM Trans. Graph. (TOG), 33(4):1-11, 2014.","title":"Reflectance scanning: Estimating shading frame and brdf with generalized linear light sources","authors":"Guojun Chen, Yue Dong, Pieter Peers","year":"2014","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2019] Wenzheng Chen, Huan Ling, Jun Gao, and et al. Learning to predict 3d objects with an interpolation-based differentiable renderer. Advances in NeurIPS, 32, 2019.","title":"Learning to predict 3d objects with an interpolation-based differentiable renderer","authors":"Chen","year":"2019","venue":"Advances in NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cook and Torrance, 1982] Robert L Cook and Kenneth E. Torrance. A reflectance model for computer graphics. ACM Trans. Graph. (TOG), 1(1):7-24, 1982.","title":"A reflectance model for computer graphics","authors":"L Robert, Kenneth E Cook, Torrance","year":"1982","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dong et al., 2010] Yue Dong, Jiaping Wang, Xin Tong, and et al. Manifold bootstrapping for svbrdf capture. ACM Trans. Graph. (TOG), 29(4):1-10, 2010.","title":"Manifold bootstrapping for svbrdf capture","authors":"Yue Dong, Jiaping Wang, Xin Tong","year":"2010","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dong et al., 2015] Zhao Dong, Bruce Walter, Steve Marschner, and et al. Predicting appearance from measured microgeometry of metal surfaces. ACM Trans. Graph. (TOG), 35(1):1-13, 2015.","title":"Predicting appearance from measured microgeometry of metal surfaces","authors":"Zhao Dong, Bruce Walter, Steve Marschner","year":"2015","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gao et al., 2019] Duan Gao, Xiao Li, Yue Dong, and et al. Deep inverse rendering for high-resolution svbrdf estima- tion from an arbitrary number of images. ACM Trans. Graph. (TOG), 38(4):134-1, 2019.","title":"Deep inverse rendering for high-resolution svbrdf estimation from an arbitrary number of images","authors":"Duan Gao, Xiao Li, Yue Dong","year":"2019","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Holroyd et al., 2010] Michael Holroyd, Jason Lawrence, and Todd Zickler. A coaxial optical scanner for syn- chronous acquisition of 3d geometry and surface re- flectance. ACM Trans. Graph. (TOG), 29(4):1-12, 2010.","title":"A coaxial optical scanner for synchronous acquisition of 3d geometry and surface reflectance","authors":"Michael Holroyd, Jason Lawrence, Todd Zickler","year":"2010","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kajiya, 1986] James T Kajiya. The rendering equation. In Proceedings of the 13th ACM SIGGRAPH, pages 143-150, 1986.","title":"The rendering equation","authors":"T James, Kajiya","year":"1986","venue":"Proceedings of the 13th ACM SIGGRAPH","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kang et al., 2018] Kaizhang Kang, Zimin Chen, Jiaping Wang, and et al. Efficient reflectance capture using an autoencoder. ACM Trans. Graph. (TOG), 37(4):127-1, 2018.","title":"Efficient reflectance capture using an autoencoder","authors":"Kang","year":"2018","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kato and Harada, 2019] Hiroharu Kato and Tatsuya Harada. Learning view priors for single-view 3d reconstruction. In Proceedings of the IEEE/CVF CVPR, pages 9778-9787, 2019.","title":"Learning view priors for single-view 3d reconstruction","authors":"Harada Kato, Hiroharu Kato, Tatsuya Harada","year":"2019","venue":"Proceedings of the IEEE/CVF CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kato et al., 2018] Hiroharu Kato, Yoshitaka Ushiku, and Tat- suya Harada. Neural 3d mesh renderer. In Proceedings of the IEEE/CVF CVPR, pages 3907-3916, 2018.","title":"Neural 3d mesh renderer","authors":"Kato","year":"2018","venue":"Proceedings of the IEEE/CVF CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kato et al., 2020] Hiroharu Kato, Deniz Beker, Mihai Morariu, and et al. Differentiable rendering: A survey. arXiv preprint arXiv:2006.12057, 2020.","title":"Differentiable rendering: A survey","authors":"Hiroharu Kato, Deniz Beker, Mihai Morariu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kazhdan and Hoppe, 2013] Michael Kazhdan and Hugues Hoppe. Screened poisson surface reconstruction. ACM Trans. Graph. (TOG), 32(3):1-13, 2013.","title":"Screened poisson surface reconstruction","authors":"Michael Kazhdan, Hugues Hoppe","year":"2013","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kazhdan et al., 2006] Michael Kazhdan, Matthew Bolitho, and Hugues Hoppe. Poisson surface reconstruction. In Proceedings of the fourth Eurographics SGP, volume 7, 2006.","title":"Poisson surface reconstruction","authors":"Matthew Michael Kazhdan, Hugues Bolitho, Hoppe","year":"2006","venue":"Proceedings of the fourth Eurographics SGP","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kim et al., 2017] Kihwan Kim, Jinwei Gu, Stephen Tyree, and et al. A lightweight approach for on-the-fly reflectance estimation. In Proceedings of the IEEE ICCV, pages 20-28, 2017.","title":"A lightweight approach for on-the-fly reflectance estimation","authors":"Kim","year":"2017","venue":"Proceedings of the IEEE ICCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lensch et al., 2003] Hendrik PA Lensch, Jan Kautz, Michael Goesele, and et al. Image-based reconstruction of spatial ap- pearance and geometric detail. ACM Trans. Graph. (TOG), 22(2):234-257, 2003.","title":"Image-based reconstruction of spatial appearance and geometric detail","authors":"P A Hendrik, Jan Lensch, Michael Kautz, Goesele","year":"2003","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Li et al., 2018a] Tzu-Mao Li, Miika Aittala, Frédo Durand, and et al. Differentiable monte carlo ray tracing through edge sampling. ACM Trans. Graph. (TOG), 37(6):1-11, 2018.","title":"Differentiable monte carlo ray tracing through edge sampling","authors":"Li","year":"2018","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Li et al., 2018b] Zhengqin Li, Kalyan Sunkavalli, and Man- mohan Chandraker. Materials for masses: Svbrdf acquisi- tion with a single mobile phone image. In Proceedings of the ECCV, pages 72-87, 2018.","title":"Zhengqin Li, Kalyan Sunkavalli, and Manmohan Chandraker. Materials for masses: Svbrdf acquisition with a single mobile phone image","authors":"Li","year":"2018","venue":"Proceedings of the ECCV","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Li et al., 2021] Rui Li, Guangmin Zang, Miao Qi, and et al. Shape and reflectance reconstruction in uncontrolled en- vironments by differentiable rendering. arXiv preprint arXiv:2110.12975, 2021.","title":"Shape and reflectance reconstruction in uncontrolled environments by differentiable rendering","authors":"Rui Li, Guangmin Zang, Miao Qi","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Liu et al., 2019] Shichen Liu, Tianye Li, Weikai Chen, and et al. Soft rasterizer: A differentiable renderer for image- based 3d reasoning. In Proceedings of the IEEE/CVF ICCV, pages 7708-7717, 2019.","title":"Soft rasterizer: A differentiable renderer for imagebased 3d reasoning","authors":"Liu","year":"2019","venue":"Proceedings of the IEEE/CVF ICCV","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Loper and Black, 2014] Matthew M Loper and Michael J Black. Opendr: An approximate differentiable renderer. In Proceedings of the ECCV, pages 154-169. Springer, 2014.","title":"Opendr: An approximate differentiable renderer","authors":"M Matthew, Michael J Loper, Black","year":"2014","venue":"Proceedings of the ECCV","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Lorensen and Cline, 1987] William E Lorensen and Har- vey E Cline. Marching cubes: A high resolution 3d surface construction algorithm. Proceedings of the 14th ACM SIG- GRAPH, 21(4):163-169, 1987.","title":"Marching cubes: A high resolution 3d surface construction algorithm","authors":"E William, Harvey E Lorensen, Cline","year":"1987","venue":"Proceedings of the 14th ACM SIG-GRAPH","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Luan et al., 2021] Fujun Luan, Shuang Zhao, Kavita Bala, and et al. Unified shape and svbrdf recovery using differen- tiable monte carlo rendering. In Computer Graphics Forum, volume 40, pages 101-113, 2021.","title":"Unified shape and svbrdf recovery using differentiable monte carlo rendering","authors":"Luan","year":"2021","venue":"Computer Graphics Forum","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Matusik, 2003] Wojciech Matusik. A data-driven reflectance model. PhD thesis, Massachusetts Institute of Technology, 2003.","title":"A data-driven reflectance model","authors":"Wojciech Matusik","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Mildenhall et al., 2020] Ben Mildenhall, Pratul P. Srini- vasan, Matthew Tancik, and et al. Nerf: Representing scenes as neural radiance fields for view synthesis. In Proceedings of the ECCV, 2020.","title":"Nerf: Representing scenes as neural radiance fields for view synthesis","authors":"Ben Mildenhall, P Pratul, Matthew Srinivasan, Tancik","year":"2020","venue":"Proceedings of the ECCV","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Munkberg et al., 2021] Jacob Munkberg, Jon Hasselgren, Tianchang Shen, and et al. Extracting triangular 3d mod- els, materials, and lighting from images. arXiv preprint arXiv:2111.12503, 2021.","title":"Extracting triangular 3d models, materials, and lighting from images","authors":"Jacob Munkberg, Jon Hasselgren, Tianchang Shen","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Nealen et al., 2006] Andrew Nealen, Takeo Igarashi, Olga Sorkine, and et al. Laplacian mesh optimization. In Pro- ceedings of the 4th international conference on Computer graphics and interactive techniques in Australasia and Southeast Asia, pages 381-389, 2006.","title":"Laplacian mesh optimization","authors":"Andrew Nealen, Takeo Igarashi, Olga Sorkine","year":"2006","venue":"Proceedings of the 4th international conference on Computer graphics and interactive techniques in Australasia and Southeast Asia","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Nimier-David et al., 2019] Merlin Nimier-David, Delio Vicini, Tizian Zeltner, and et al. Mitsuba 2: A retargetable forward and inverse renderer. ACM Trans. Graph. (TOG), 38(6):1-17, 2019.","title":"Mitsuba 2: A retargetable forward and inverse renderer","authors":"Nimier-David","year":"2019","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Park et al., 2018] Jeong Joon Park, Richard Newcombe, and Steve Seitz. Surface light field fusion. In 2018 International Conference on 3D Vision (3DV), pages 12-21. IEEE, 2018.","title":"Surface light field fusion","authors":"Jeong Joon Park, Richard Newcombe, Steve Seitz","year":"2018","venue":"International Conference on 3D Vision (3DV)","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Patow and Pueyo, 2003] Gustavo Patow and Xavier Pueyo. A survey of inverse rendering problems. In Computer Graphics Forum, volume 22, pages 663-687, 2003.","title":"Gustavo Patow and Xavier Pueyo. A survey of inverse rendering problems","authors":"Pueyo Patow","year":"2003","venue":"Computer Graphics Forum","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Ravi et al., 2020] Nikhila Ravi, Jeremy Reizenstein, David Novotny, and et al. Accelerating 3d deep learning with pytorch3d. arXiv preprint arXiv:2007.08501, 2020.","title":"Accelerating 3d deep learning with pytorch3d","authors":"Nikhila Ravi, Jeremy Reizenstein, David Novotny","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Remelli et al., 2020] Edoardo Remelli, Artem Lukoianov, Stephan Richter, and et al. Meshsdf: Differentiable iso- surface extraction. Advances in Neural Information Pro- cessing Systems, 33:22468-22478, 2020.","title":"Meshsdf: Differentiable isosurface extraction","authors":"Edoardo Remelli, Artem Lukoianov, Stephan Richter","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Schmitt et al., 2020] Carolin Schmitt, Simon Donne, Gernot Riegler, and et al. On joint estimation of pose, geometry and svbrdf from a handheld scanner. In Proceedings of the IEEE/CVF CVPR, pages 3493-3503, 2020.","title":"On joint estimation of pose, geometry and svbrdf from a handheld scanner","authors":"Carolin Schmitt, Simon Donne, Gernot Riegler","year":"2020","venue":"Proceedings of the IEEE/CVF CVPR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Schonberger and Frahm, 2016] Johannes L Schonberger and Jan-Michael Frahm. Structure-from-motion revisited. In Proceedings of the IEEE CVPR, pages 4104-4113, 2016.","title":"Structure-from-motion revisited","authors":"Frahm ; Schonberger, L Johannes, Jan-Michael Schonberger, Frahm","year":"2016","venue":"Proceedings of the IEEE CVPR","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Schönberger et al., 2016] Johannes L Schönberger, Enliang Zheng, Jan-Michael Frahm, and et al. Pixelwise view se- lection for unstructured multi-view stereo. In Proceedings of the ECCV, pages 501-518. Springer, 2016.","title":"Pixelwise view selection for unstructured multi-view stereo","authors":"Schönberger","year":"2016","venue":"Proceedings of the ECCV","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Srinivasan et al., 2021] Pratul P Srinivasan, Boyang Deng, Xiuming Zhang, and et al. Nerv: Neural reflectance and visibility fields for relighting and view synthesis. In Pro- ceedings of the IEEE/CVF CVPR, pages 7495-7504, 2021.","title":"Nerv: Neural reflectance and visibility fields for relighting and view synthesis","authors":"Boyang Pratul P Srinivasan, Xiuming Deng, Zhang","year":"2021","venue":"Proceedings of the IEEE/CVF CVPR","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Walter et al., 2007] Bruce Walter, Stephen R Marschner, Hongsong Li, and et al. Microfacet models for refraction through rough surfaces. Rendering techniques, 2007:18th, 2007.","title":"Microfacet models for refraction through rough surfaces","authors":"Bruce Walter, Hongsong Stephen R Marschner, Li","year":"2007","venue":"Rendering techniques","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Wang et al., 2018] Nanyang Wang, Yinda Zhang, Zhuwen Li, and et al. Pixel2mesh: Generating 3d mesh models from single rgb images. In Proceedings of the ECCV, pages 52-67, 2018.","title":"Pixel2mesh: Generating 3d mesh models from single rgb images","authors":"Wang","year":"2018","venue":"Proceedings of the ECCV","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Wu et al., 2020] Shangzhe Wu, Christian Rupprecht, and Andrea Vedaldi. Unsupervised learning of probably sym- metric deformable 3d objects from images in the wild. In Proceedings of the IEEE/CVF CVPR, pages 1-10, 2020.","title":"Unsupervised learning of probably symmetric deformable 3d objects from images in the wild","authors":"Wu","year":"2020","venue":"Proceedings of the IEEE/CVF CVPR","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Yariv et al., 2020] Lior Yariv, Yoni Kasten, Dror Moran, and et al. Multiview neural surface reconstruction by disen- tangling geometry and appearance. Advances in NeurIPS, 33:2492-2502, 2020.","title":"Multiview neural surface reconstruction by disentangling geometry and appearance","authors":"Lior Yariv, Yoni Kasten, Dror Moran","year":"2020","venue":"Advances in NeurIPS","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Zeltner et al., 2021] Tizian Zeltner, Sébastien Speierer, Iliyan Georgiev, and et al. Monte carlo estimators for dif- ferential light transport. ACM Trans. Graph. (TOG), 40(4), August 2021.","title":"Monte carlo estimators for differential light transport","authors":"Tizian Zeltner, Sébastien Speierer, Iliyan Georgiev","year":"2021","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zhang et al., 2018] Richard Zhang, Phillip Isola, Alexei A Efros, and et al. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE/CVF CVPR, pages 586-595, 2018.","title":"The unreasonable effectiveness of deep features as a perceptual metric","authors":"Richard Zhang, Phillip Isola, Alexei A Efros","year":"2018","venue":"Proceedings of the IEEE/CVF CVPR","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zhang et al., 2019] Cheng Zhang, Lifan Wu, Changxi Zheng, and et al. A differential theory of radiative transfer. ACM Trans. Graph. (TOG), 38(6):1-16, 2019.","title":"A differential theory of radiative transfer","authors":"Cheng Zhang, Lifan Wu, Changxi Zheng","year":"2019","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Zhang et al., 2021a] Jason Zhang, Gengshan Yang, Shub- ham Tulsiani, and et al. Ners: Neural reflectance surfaces for sparse-view 3d reconstruction in the wild. Advances in NeurIPS, 34:29835-29847, 2021.","title":"Ners: Neural reflectance surfaces for sparse-view 3d reconstruction in the wild","authors":"Zhang","year":"2021","venue":"Advances in NeurIPS","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Zhang et al., 2021b] Kai Zhang, Fujun Luan, Qianqian Wang, and et al. Physg: Inverse rendering with spherical gaussians for physics-based material editing and relighting. In Proceedings of the IEEE/CVF CVPR, pages 5453-5462, 2021.","title":"Physg: Inverse rendering with spherical gaussians for physics-based material editing and relighting","authors":"Zhang","year":"2021","venue":"Proceedings of the IEEE/CVF CVPR","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Zhang et al., 2021c] Xiuming Zhang, Pratul P Srinivasan, Boyang Deng, and et al. Nerfactor: Neural factorization of shape and reflectance under an unknown illumination. ACM Trans. Graph. (TOG), 40(6):1-18, 2021.","title":"Nerfactor: Neural factorization of shape and reflectance under an unknown illumination","authors":"Zhang","year":"2021","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Zhang et al., 2022] Kai Zhang, Fujun Luan, Zhengqi Li, and et al. Iron: Inverse rendering by optimizing neural sdfs and materials from photometric images. In Proceedings of the IEEE/CVF CVPR, pages 5565-5574, 2022.","title":"Iron: Inverse rendering by optimizing neural sdfs and materials from photometric images","authors":"Kai Zhang, Fujun Luan, Zhengqi Li","year":"2022","venue":"Proceedings of the IEEE/CVF CVPR","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Zhou et al., 2016] Zhiming Zhou, Guojun Chen, Yue Dong, and et al. Sparse-as-possible svbrdf acquisition. ACM Trans. Graph. (TOG), 35(6):1-12, 2016.","title":"Sparse-as-possible svbrdf acquisition","authors":"Zhiming Zhou, Guojun Chen, Yue Dong","year":"2016","venue":"ACM Trans. Graph. (TOG)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}