Self-supervised Outdoor Scene Relighting

Outdoor scene relighting is a challenging problem that requires good understanding of the scene geometry, illumination and albedo. Current techniques are completely supervised, requiring high quality synthetic renderings to train a solution. Such renderings are synthesized using priors learned from limited data. In contrast, we propose a self-supervised approach for relighting. Our approach is trained only on corpora of images collected from the internet without any user-supervision. This virtually endless source of training data allows training a general relighting solution. Our approach first decomposes an image into its albedo, geometry and illumination. A novel relighting is then produced by modifying the illumination parameters. Our solution capture shadow using a dedicated shadow prediction map, and does not rely on accurate geometry estimation. We evaluate our technique subjectively and objectively using a new dataset with ground-truth relighting. Results show the ability of our technique to produce photo-realistic and physically plausible results, that generalizes to unseen scenes.

[1]  Adrien Bousseau,et al.  Multiview Intrinsic Images of Outdoors Scenes with an Application to Relighting , 2015, ACM Trans. Graph..

[2]  Jan Kautz,et al.  Neural Inverse Rendering of an Indoor Scene From a Single Image , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4]  Kalyan Sunkavalli,et al.  Fast Spatially-Varying Indoor Lighting Estimation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Qunsheng Peng,et al.  Lighting Simulation of Augmented Outdoor Scene Based on a Legacy Photograph , 2013, Comput. Graph. Forum.

[6]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[7]  Steven M. Seitz,et al.  The Visual Turing Test for Scene Reconstruction , 2013, 2013 International Conference on 3D Vision.

[8]  Yannick Hold-Geoffroy,et al.  Deep Outdoor Illumination Estimation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Jitendra Malik,et al.  Shape, Illumination, and Reflectance from Shading , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Ersin Yumer,et al.  Neural Face Editing with Intrinsic Image Disentangling , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Pat Hanrahan,et al.  An efficient representation for irradiance environment maps , 2001, SIGGRAPH.

[12]  Ye Yu,et al.  InverseRenderNet: Learning Single Image Inverse Rendering , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Zhengqi Li,et al.  MegaDepth: Learning Single-View Depth Prediction from Internet Photos , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Ning Xu,et al.  End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Jitendra Malik,et al.  Recovering photometric properties of architectural scenes from photographs , 1998, SIGGRAPH.

[16]  Paul E. Debevec,et al.  Unlighting the Parthenon , 2004, SIGGRAPH '04.

[17]  Gustavo Patow,et al.  A Survey of Inverse Rendering Problems , 2003, Comput. Graph. Forum.

[18]  Alexei A. Efros,et al.  Webcam clip art: appearance and illuminant transfer from time-lapse sequences , 2009, ACM Trans. Graph..

[19]  Justus Thies,et al.  Deferred Neural Rendering: Image Synthesis using Neural Textures , 2019 .

[20]  Pierre Poulin,et al.  Interactive Virtual Relighting and Remodeling of Real Scenes , 1999, Rendering Techniques.

[21]  Paul E. Debevec,et al.  Image-based lighting , 2002, IEEE Computer Graphics and Applications.

[22]  Sylvain Paris,et al.  Deep Photo Style Transfer , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Taesung Park,et al.  Semantic Image Synthesis With Spatially-Adaptive Normalization , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Wojciech Matusik,et al.  Factored time-lapse video , 2007, ACM Trans. Graph..

[25]  PeersPieter,et al.  Relighting with 4D incident light fields , 2003 .

[26]  Dani Lischinski,et al.  Deep photo: model-based photograph enhancement and viewing , 2008, SIGGRAPH Asia '08.

[27]  Andrew Jones,et al.  Direct HDR capture of the sun and sky , 2006, SIGGRAPH Courses.

[28]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[29]  Kalyan Sunkavalli,et al.  Deep image-based relighting from optimal sparse samples , 2018, ACM Trans. Graph..

[30]  Hans-Peter Seidel,et al.  LIME: Live Intrinsic Material Estimation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[31]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[32]  David W. Jacobs,et al.  Deep Single-Image Portrait Relighting , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[33]  Hans-Peter Seidel,et al.  Relighting objects from image collections , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Zhengqi Li,et al.  Learning Intrinsic Image Decomposition from Watching the World , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[35]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Christian Theobalt,et al.  Live User-Guided Intrinsic Video for Static Scenes , 2017, IEEE Transactions on Visualization and Computer Graphics.

[37]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[39]  Alexei A. Efros,et al.  Estimating the Natural Illumination Conditions from a Single Outdoor Image , 2012, International Journal of Computer Vision.

[40]  Paul Debevec,et al.  Inverse global illumination: Recovering re?ectance models of real scenes from photographs , 1998 .

[41]  Andrew Gardner,et al.  Performance relighting and reflectance transformation with time-multiplexed illumination , 2005, ACM Trans. Graph..

[42]  Paul E. Debevec,et al.  Acquiring the reflectance field of a human face , 2000, SIGGRAPH.

[43]  Adrien Bousseau,et al.  Coherent intrinsic images from photo collections , 2012, ACM Trans. Graph..

[44]  Peter K. Allen,et al.  Building Illumination Coherent 3D Models of Large-Scale Outdoor Scenes , 2008, International Journal of Computer Vision.

[45]  Steven M. Seitz,et al.  LookinGood , 2018, ACM Trans. Graph..

[46]  Pieter Peers,et al.  Relighting with 4D incident light fields , 2003, ACM Trans. Graph..

[47]  David A. Forsyth,et al.  Rendering synthetic objects into legacy photographs , 2011, ACM Trans. Graph..

[48]  George Drettakis,et al.  Multi-view relighting using a geometry-aware network , 2019, ACM Trans. Graph..

[49]  Noah Snavely,et al.  Neural Rerendering in the Wild , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  Frédo Durand,et al.  Data-driven hallucination of different times of day from a single outdoor photo , 2013, ACM Trans. Graph..

[51]  Yasuyuki Matsushita,et al.  Single-View Relighting with Normal Map Painting , 2006 .