“Intrinsic Image Decomposition via Ordinal Shading” – ACM SIGGRAPH HISTORY ARCHIVES

“Intrinsic Image Decomposition via Ordinal Shading”

  • ©

Conference:


Type(s):


Title:

    Intrinsic Image Decomposition via Ordinal Shading

Presenter(s)/Author(s):



Abstract:


    We achieve high-resolution intrinsic decomposition in the wild. Our approach consists of two steps: estimating dense ordinal shading cues, and combining low- and high-resolution ordinal estimations to achieve coherent and detailed shading. Our method allows us to generate dense supervision from multi-illumination data resulting in generalization to diverse scenes.

References:


    [1]
    A. S. Baslamisli, T. T. Groenestege, P. Das, H. A. Le, S. Karaoglu, and T. Gevers. 2018a. Joint learning of intrinsic images and semantic segmentation. In Proc. ECCV.

    [2]
    Anil S. Baslamisli, Hoang-An Le, and Theo Gevers. 2018b. CNN based learning using reflection and Retinex models for intrinsic image decomposition. In Proc. CVPR.

    [3]
    Sean Bell, Kavita Bala, and Noah Snavely. 2014. Intrinsic images in the wild. ACM Trans. Graph. 33, 4 (2014), 1?12.

    [4]
    Sai Bi, Nima Khademi Kalantari, and Ravi Ramamoorthi. 2018. Deep hybrid real and synthetic training for intrinsic decomposition. In Proc. EGSR.

    [5]
    Nicolas Bonneel, Balazs Kovacs, Sylvain Paris, and Kavita Bala. 2017. Intrinsic decompositions for image editing. Comput. Graph. Forum 36, 2 (2017).

    [6]
    D. J. Butler, J. Wulff, G. B. Stanley, and M. J. Black. 2012. A naturalistic open source movie for optical flow evaluation. In Proc. ECCV.

    [7]
    Angel X. Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, Jianxiong Xiao, Li Yi, and Fisher Yu. 2015. ShapeNet: An Information-Rich 3D Model Repository. Technical Report arXiv:1512.03012 [cs.GR]. Stanford University ? Princeton University ? Toyota Technological Institute at Chicago.

    [8]
    L. Cheng, C. Zhang, and Z. Liao. 2018. Intrinsic image transformation via scale space decomposition. In Proc. CVPR.

    [9]
    Partha Das, Sezer Karaoglu, and Theo Gevers. 2022. PIE-Net: Photometric invariant edge guided network for intrinsic image decomposition. In Proc. CVPR.

    [10]
    Ainaz Eftekhar, Alexander Sax, Jitendra Malik, and Amir Zamir. 2021. Omnidata: A scalable pipeline for making multi-task mid-level vision datasets from 3D scans. In Proc. ICCV.

    [11]
    Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, and David Wipf. 2018. Revisiting deep intrinsic image decompositions. In Proc. CVPR.

    [12]
    Elena Garces, Adolfo Munoz, Jorge Lopez-Moreno, and Diego Gutierrez. 2012. Intrinsic images by clustering. Comput. Graph. Forum 31, 4 (2012), 1415?1424.

    [13]
    Elena Garces, Carlos Rodriguez-Pardo, Dan Casas, and Jorge Lopez-Moreno. 2022. A survey on intrinsic images: Delving deep into Lambert and beyond. Int. J. Comput. Vision (2022).

    [14]
    Roger Grosse, Micah Johnson, Edward Adelson, and William Freeman. 2009. Ground truth dataset and baseline evaluations for intrinsic image algorithms. In Proc. ICCV.

    [15]
    Michael Janner, Jiajun Wu, Tejas Kulkarni, Ilker Yildirim, and Joshua B. Tenenbaum. 2017. Self-supervised intrinsic image decomposition. In Proc. NeurIPS.

    [16]
    Balazs Kovacs, Sean Bell, Noah Snavely, and Kavita Bala. 2017. Shading annotations in the wild. Proc. CVPR.

    [17]
    Philipp Krahenbuhl. 2018. Free supervision from video games. In Proc. CVPR.

    [18]
    Hoang-An Le, Partha Das, Thomas Mensink, Sezer Karaoglu, and Theo Gevers. 2021. EDEN: Multimodal synthetic dataset of enclosed garden scenes. In Proc. WACV.

    [19]
    Louis Lettry, Kenneth Vanhoey, and Luc Van Gool. 2018a. DARN: A deep adversarial residual network for intrinsic image decomposition. Proc. WACV.

    [20]
    L. Lettry, K. Vanhoey, and L. Van Gool. 2018b. Unsupervised deep single-image intrinsic decomposition using illumination-varying image sequences. Comput. Graph. Forum 37, 7 (2018), 409?419.

    [21]
    Zhengqin Li, Mohammad Shafiei, Ravi Ramamoorthi, Kalyan Sunkavalli, and Manmohan Chandraker. 2020. Inverse rendering for complex indoor scenes: Shape, spatially-varying lighting and SVBRDF from a single image. In Proc. CVPR.

    [22]
    Zhengqi Li and Noah Snavely. 2018a. CGIntrinsics: Better intrinsic image decomposition through physically-based rendering. In Proc. ECCV.

    [23]
    Zhengqi Li and Noah Snavely. 2018b. Learning intrinsic image decomposition from watching the world. In Proc. CVPR.

    [24]
    Zhengqi Li and Noah Snavely. 2018c. MegaDepth: Learning single-view depth prediction from Internet photos. In Proc. CVPR.

    [25]
    Zhengqin Li, Ting Yu, Shen Sang, Sarah Wang, Mengcheng Song, Yuhan Liu, Yu-Ying Yeh, Rui Zhu, Nitesh B. Gundavarapu, Jia Shi, Sai Bi, Hong-Xing Yu, Zexiang Xu, Kalyan Sunkavalli, Milo? Ha?an, Ravi Ramamoorthi, and Manmohan Chandraker. 2021. OpenRooms: An open framework for photorealistic indoor scene datasets. Proc. CVPR.

    [26]
    G. Lin, A. Milan, C. Shen, and I. Reid. 2017. RefineNet: Multi-path refinement networks for high-resolution semantic segmentation. In Proc. CVPR.

    [27]
    Yunfei Liu, Yu Li, Shaodi You, and Feng Lu. 2020. Unsupervised learning for intrinsic image decomposition from a single image. In Proc. CVPR.

    [28]
    Jundan Luo, Zhaoyang Huang, Yijin Li, Xiaowei Zhou, Guofeng Zhang, and Hujun Bao. 2020. NIID-Net: Adapting surface normal knowledge for intrinsic image decomposition in indoor scenes. IEEE Trans. Vis. Comp. Graph. (2020).

    [29]
    Wei-Chiu Ma, Hang Chu, Bolei Zhou, Raquel Urtasun, and Antonio Torralba. 2018. Single image intrinsic decomposition without a single intrinsic image. In Proc. ECCV.

    [30]
    Abhimitra Meka, Maxim Maximov, Michael Zollhoefer, Avishek Chatterjee, Hans-Peter Seidel, Christian Richardt, and Christian Theobalt. 2018. LIME: Live intrinsic material estimation. In Proc. CVPR.

    [31]
    S. Mahdi H. Miangoleh, Sebastian Dille, Long Mai, Sylvain Paris, and Ya??z Aksoy. 2021. Boosting monocular depth estimation models to high-resolution via content-adaptive multi-resolution merging. In Proc. CVPR.

    [32]
    Lukas Murmann, Michael Gharbi, Miika Aittala, and Fredo Durand. 2019. A multi-illumination dataset of indoor object appearance. In Proc. ICCV.

    [33]
    Takuya Narihira, Michael Maire, and Stella X. Yu. 2015. Learning lightness from human judgement on relative reflectance. In Proc. CVPR.

    [34]
    Thomas Nestmeyer and Peter V. Gehler. 2017. Reflectance adaptive filtering improves intrinsic image estimation. In Proc. CVPR.

    [35]
    Patrick P?rez, Michel Gangnet, and Andrew Blake. 2003. Poisson image editing. In ACM SIGGRAPH. 313?318.

    [36]
    Ren? Ranftl, Katrin Lasinger, David Hafner, Konrad Schindler, and Vladlen Koltun. 2020. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. (2020).

    [37]
    Mike Roberts, Jason Ramapuram, Anurag Ranjan, Atulit Kumar, Miguel Angel Bautista, Nathan Paczan, Russ Webb, and Joshua M. Susskind. 2021. Hypersim: A photorealistic synthetic dataset for holistic indoor scene understanding. In Proc. ICCV.

    [38]
    Soumyadip Sengupta, Jinwei Gu, Kihwan Kim, Guilin Liu, David W. Jacobs, and Jan Kautz. 2019. Neural inverse rendering of an indoor scene from a single image. In Proc. ICCV.

    [39]
    Jianbing Shen, Xiaoshan Yang, Yunde Jia, and Xuelong Li. 2011. Intrinsic images using optimization. In Proc. CVPR.

    [40]
    Jian Shi, Yue Dong, Hao Su, and Stella X. Yu. 2017. Learning non-Lambertian object intrinsics across ShapeNet categories. In Proc. CVPR.

    [41]
    Michael Maire, Takuya Narihira and Stella X. Yu. 2015. Direct intrinsics: Learning albedo-shading decomposition by convolutional regression. In Proc. ICCV.

    [42]
    Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proc. ICML.

    [43]
    Ke Xian, Jianming Zhang, Oliver Wang, Long Mai, Zhe Lin, and Zhiguo Cao. 2020. Structure-guided ranking loss for single image depth prediction. In Proc. CVPR.

    [44]
    Saining Xie, Ross Girshick, Piotr Doll?r, Zhuowen Tu, and Kaiming He. 2017. Aggregated residual transformations for deep neural networks. In Proc. CVPR.

    [45]
    Genzhi Ye, Elena Garces, Yebin Liu, Qionghai Dai, and Diego Gutierrez. 2014. Intrinsic video and applications. ACM Trans. Graph. 33, 4 (2014).

    [46]
    Qi Zhao, Ping Tan, Qiang Dai, Li Shen, Enhua Wu, and Stephen Lin. 2012. A closed-form solution to Retinex with nonlocal texture constraints. IEEE Trans. Pattern Anal. Mach. Intell. 34, 7 (2012), 1437?1444.

    [47]
    Hao Zhou, Xiang Yu, and David Jacobs. 2019. GLoSH: Global-local spherical harmonics for intrinsic image decomposition. In Proc. ICCV.

    [48]
    Tinghui Zhou, Philipp Krahenbuhl, and Alexei A. Efros. 2015. Learning data-driven reflectance priors for intrinsic image decomposition. In Proc. ICCV.

    [49]
    Rui Zhu, Zhengqin Li, Janarbek Matai, Fatih Porikli, and Manmohan Chandraker. 2022. IRISformer: Dense vision transformers for single-image inverse rendering in indoor scenes. In Proc. CVPR.

    [50]
    Daniel Zoran, Phillip Isola, Dilip Krishnan, and William Freeman. 2015. Learning ordinal relationships for mid-level vision. In Proc. ICCV.


ACM Digital Library Publication:



Overview Page:



Submit a story:

If you would like to submit a story about this presentation, please contact us: historyarchives@siggraph.org