Plausible Shading Decomposition For Layered Photo Retouching

Photographers routinely compose multiple manipulated photos of the same scene (layers) into a single image, which is better than any individual photo could be alone. Similarly, 3D artists set up rendering systems to produce layered images to contain only individual aspects of the light transport, which are composed into the final result in post-production. Regrettably, both approaches either take considerable time to capture, or remain limited to synthetic scenes. In this paper, we suggest a system to allow decomposing a single image into a plausible shading decomposition (PSD) that approximates effects such as shadow, diffuse illumination, albedo, and specular shading. This decomposition can then be manipulated in any off-the-shelf image manipulation software and recomposited back. We perform such a decomposition by learning a convolutional neural network trained using synthetic data. We demonstrate the effectiveness of our decomposition on synthetic (i.e., rendered) and real data (i.e., photographs), and use them for common photo manipulation, which are nearly impossible to perform otherwise from single images.

[1]  Noah Snavely,et al.  Intrinsic images in the wild , 2014, ACM Trans. Graph..

[2]  Eric P. Lafortune,et al.  Using the modified Phong reflectance model for physically based rendering , 1994 .

[3]  Frédo Durand,et al.  User-guided white balance for mixed lighting conditions , 2012, ACM Trans. Graph..

[4]  Sylvain Paris,et al.  User-assisted image compositing for photographic lighting , 2013, ACM Trans. Graph..

[5]  Szymon Rusinkiewicz,et al.  Exaggerated shading for depicting shape and detail , 2006, ACM Trans. Graph..

[6]  Maneesh Agrawala,et al.  Illumination decomposition for material recoloring with consistent interreflections , 2011, ACM Trans. Graph..

[7]  Rob Fergus,et al.  Depth Map Prediction from a Single Image using a Multi-Scale Deep Network , 2014, NIPS.

[8]  英樹 藤堂,et al.  Interactive intrinsic video editing , 2014, ACM Trans. Graph..

[9]  Stella X. Yu,et al.  Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[11]  Eli Shechtman,et al.  StyLit , 2016, ACM Trans. Graph..

[12]  Alexei A. Efros,et al.  Estimating natural illumination from a single outdoor image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[13]  William V. Baxter,et al.  Locally controllable stylized shading , 2007, ACM Trans. Graph..

[14]  Wei Yang,et al.  Ambient occlusion via compressive visibility estimation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Sylvain Paris,et al.  User-assisted intrinsic images , 2009, ACM Trans. Graph..

[16]  Baining Guo,et al.  AppGen: interactive material modeling from a single image , 2011, ACM Trans. Graph..

[17]  David J. Kriegman,et al.  Specularity Removal in Images and Videos: A PDE Approach , 2006, ECCV.

[18]  Qionghai Dai,et al.  Intrinsic video and applications , 2014, ACM Trans. Graph..

[19]  Derek Nowrouzezahrai,et al.  State of the Art in Artistic Editing of Appearance, Lighting and Material , 2016, Comput. Graph. Forum.

[20]  Leonidas J. Guibas,et al.  ShapeNet: An Information-Rich 3D Model Repository , 2015, ArXiv.

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

[22]  Jan Kautz,et al.  Exposure Fusion , 2009, 15th Pacific Conference on Computer Graphics and Applications (PG'07).

[23]  Hans-Peter Seidel,et al.  Approximating dynamic global illumination in image space , 2009, I3D '09.

[24]  Jaakko Lehtinen,et al.  Two-shot SVBRDF capture for stationary materials , 2015, ACM Trans. Graph..

[25]  Noah Snavely,et al.  Photometric Ambient Occlusion , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Adolfo Muñoz,et al.  Intrinsic Images by Clustering , 2012, Comput. Graph. Forum.

[27]  Thomas Brox,et al.  FlowNet: Learning Optical Flow with Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[28]  Frédo Durand,et al.  A gentle introduction to bilateral filtering and its applications , 2007, SIGGRAPH Courses.

[29]  Pat Hanrahan,et al.  Conveying shape and features with image-based relighting , 2003, IEEE Visualization, 2003. VIS 2003..

[30]  Adrien Bousseau,et al.  Vectorising Bitmaps into Semi‐Transparent Gradient Layers , 2014, Comput. Graph. Forum.

[31]  Hans-Peter Seidel,et al.  Interactive on-surface signal deformation , 2010 .

[32]  Katsushi Ikeuchi,et al.  Separating reflection components based on chromaticity and noise analysis , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[35]  Paul S. Heckbert Adaptive radiosity textures for bidirectional ray tracing , 1990, SIGGRAPH.

[36]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[37]  Bo Dong,et al.  Measurement-based editing of diffuse albedo with consistent interreflections , 2015, ACM Trans. Graph..

[38]  Pascal Barla,et al.  Light warping for enhanced surface depiction , 2009, ACM Trans. Graph..

[39]  Mario Fritz,et al.  Deep Reflectance Maps , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Erik Reinhard,et al.  Image-based material editing , 2005, SIGGRAPH '05.

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

[42]  F. Durand,et al.  Flash photography enhancement via intrinsic relighting , 2004, ACM Trans. Graph..

[43]  Szymon Rusinkiewicz,et al.  Multiscale shape and detail enhancement from multi-light image collections , 2007, ACM Trans. Graph..