Automatic Reflection Removal using Gradient Intensity and Motion Cues

We present a method to separate the background image and reflection from two photos that are taken in front of a transparent glass under slightly different viewpoints. In our method, the SIFT-flow between two images is first calculated and a motion hierarchy is constructed from the SIFT-flow at multiple levels of spatial smoothness. To distinguish background edges and reflection edges, we calculate a motion score for each edge pixel by its variance along the motion hierarchy. Alternatively, we make use of the so-called superpixels to group edge pixels into edge segments and calculate the motion scores by averaging over each segment. In the meantime, we also calculate an intensity score for each edge pixel by its gradient magnitude. We combine both motion and intensity scores to get a combination score. A binary labelling (for separation) can be obtained by thresholding the combination scores. The background image is finally reconstructed from the separated gradients. Compared to the existing approaches that require a sequence of images or a video clip for the separation, we only need two images, which largely improves its feasibility. Various challenging examples are tested to validate the effectiveness of our method.

[1]  Ronen Basri,et al.  Separation of Transparent Layers using Focus , 2004, International Journal of Computer Vision.

[2]  William T. Freeman,et al.  A computational approach for obstruction-free photography , 2015, ACM Trans. Graph..

[3]  Changshui Zhang,et al.  Blindly separating mixtures of multiple layers with spatial shifts , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Toshimitsu Tanaka,et al.  Separating Real and Virtual Objects from Their Overlapping Images , 1996, ECCV.

[5]  Michal Irani,et al.  Separating transparent layers of repetitive dynamic behaviors , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[6]  Assaf Zomet,et al.  Separating reflections from a single image using local features , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[7]  Michael S. Brown,et al.  Single Image Layer Separation Using Relative Smoothness , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Ramesh Raskar,et al.  Removing photography artifacts using gradient projection and flash-exposure sampling , 2005, ACM Trans. Graph..

[9]  Michael S. Brown,et al.  Exploiting Reflection Change for Automatic Reflection Removal , 2013, 2013 IEEE International Conference on Computer Vision.

[10]  Yoav Y. Schechner,et al.  Polarization-based decorrelation of transparent layers: The inclination angle of an invisible surface , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[11]  Sung Yong Shin,et al.  A physically-based approach to reflection separation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Sung Yong Shin,et al.  High-Quality Reflection Separation Using Polarized Images , 2011, IEEE Transactions on Image Processing.

[13]  智一 吉田,et al.  Efficient Graph-Based Image Segmentationを用いた圃場図自動作成手法の検討 , 2014 .

[14]  Anat Levin,et al.  User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Antonio Torralba,et al.  SIFT Flow: Dense Correspondence across Scenes and Its Applications , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Changshui Zhang,et al.  Blind Separation of Superimposed Moving Images Using Image Statistics , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Richard Szeliski,et al.  Layer extraction from multiple images containing reflections and transparency , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).