Sparse representation of cast shadows via ℓ1-regularized least squares

Scenes with cast shadows can produce complex sets of images. These images cannot be well approximated by low-dimensional linear subspaces. However, in this paper we show that the set of images produced by a Lambertian scene with cast shadows can be efficiently represented by a sparse set of images generated by directional light sources. We first model an image with cast shadows as composed of a diffusive part (without cast shadows) and a residual part that captures cast shadows. Then, we express the problem in an ℓ1-regularized least squares formulation, with nonnegativity constraints. This sparse representation enjoys an effective and fast solution, thanks to recent advances in compressive sensing. In experiments on both synthetic and real data, our approach performs favorably in comparison to several previously proposed methods.

[1]  Serge J. Belongie,et al.  Structured importance sampling of environment maps , 2003, ACM Trans. Graph..

[2]  Paul E. Debevec,et al.  Rendering synthetic objects into real scenes: bridging traditional and image-based graphics with global illumination and high dynamic range photography , 1998, SIGGRAPH '08.

[3]  Katsushi Ikeuchi,et al.  Illumination distribution from shadows , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[4]  Takahiro Okabe,et al.  Spherical harmonics vs. Haar wavelets: basis for recovering illumination from cast shadows , 2004, CVPR 2004.

[5]  Arnold Neumaier,et al.  Solving Ill-Conditioned and Singular Linear Systems: A Tutorial on Regularization , 1998, SIAM Rev..

[6]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[7]  Pat Hanrahan,et al.  All-frequency shadows using non-linear wavelet lighting approximation , 2003, ACM Trans. Graph..

[8]  Jan Kautz,et al.  Precomputed radiance transfer for real-time rendering in dynamic, low-frequency lighting environments , 2002 .

[9]  Peter W. Hallinan A low-dimensional representation of human faces for arbitrary lighting conditions , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Guillermo Sapiro,et al.  Discriminative learned dictionaries for local image analysis , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Shree K. Nayar,et al.  Compressive Structured Light for Recovering Inhomogeneous Participating Media , 2008, ECCV.

[12]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

[13]  Takahiro Okabe,et al.  Spherical harmonics vs. Haar wavelets: basis for recovering illumination from cast shadows , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[14]  Katsushi Ikeuchi,et al.  Stability issues in recovering illumination distribution from brightness in shadows , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[15]  Paul Debevec Rendering synthetic objects into real scenes: bridging traditional and image-based graphics with global illumination and high dynamic range photography , 2008, SIGGRAPH Classes.

[16]  Katsushi Ikeuchi,et al.  Determining reflectance and light position from a single image without distant illumination assumption , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[17]  Pieter Peers,et al.  Compressive light transport sensing , 2009, ACM Trans. Graph..

[18]  Katsushi Ikeuchi,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence , 2004 .

[19]  Katsushi Ikeuchi,et al.  Illumination from Shadows , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Katsushi Ikeuchi,et al.  Determining Reflectance Parameters and Illumination Distribution from a Sparse Set of Images for View-dependent Image Synthesis , 2001, ICCV.

[21]  Pat Hanrahan,et al.  A signal-processing framework for inverse rendering , 2001, SIGGRAPH.

[22]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Volkan Cevher,et al.  Compressive Sensing for Background Subtraction , 2008, ECCV.

[24]  P. Hanrahan,et al.  On the relationship between radiance and irradiance: determining the illumination from images of a convex Lambertian object. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.

[25]  Soheil Darabi,et al.  Compressive Dual Photography , 2009, Comput. Graph. Forum.

[26]  David J. Kriegman,et al.  What is the set of images of an object under all possible lighting conditions? , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[27]  David W. Jacobs,et al.  Non-negative lighting and specular object recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[28]  K. Bala,et al.  Lightcuts: a scalable approach to illumination , 2005, SIGGRAPH 2005.

[29]  Amnon Shashua,et al.  On Photometric Issues in 3D Visual Recognition from a Single 2D Image , 2004, International Journal of Computer Vision.

[30]  Ravi Ramamoorthi,et al.  A Fourier Theory for Cast Shadows , 2004, ECCV.

[31]  David J. Kriegman,et al.  What Is the Set of Images of an Object Under All Possible Illumination Conditions? , 1998, International Journal of Computer Vision.

[32]  Ronen Basri,et al.  Lambertian Reflectance and Linear Subspaces , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Yee-Hong Yang,et al.  Illuminant direction determination for multiple light sources , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).