Locally non-rigid registration for mobile HDR photography

Image registration for stack-based HDR photography is challenging. If not properly accounted for, camera motion and scene changes result in artifacts in the composite image. Unfortunately, existing methods to address this problem are either accurate, but too slow for mobile devices, or fast, but prone to failing. We propose a method that fills this void: our approach is extremely fast - under 700ms on a commercial tablet for a pair of 5MP images - and prevents the artifacts that arise from insufficient registration quality.

[1]  Jun Hu,et al.  HDR Deghosting: How to Deal with Saturation? , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Roberto Manduchi,et al.  Metering for Exposure Stacks , 2012, Comput. Graph. Forum.

[3]  Hans-Peter Seidel,et al.  A perceptual framework for contrast processing of high dynamic range images , 2006, TAP.

[4]  Eli Shechtman,et al.  Robust patch-based hdr reconstruction of dynamic scenes , 2012, ACM Trans. Graph..

[5]  Hailin Jin,et al.  Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[7]  Greg Ward,et al.  Fast, Robust Image Registration for Compositing High Dynamic Range Photographs from Hand-Held Exposures , 2003, J. Graphics, GPU, & Game Tools.

[8]  Subhasis Chaudhuri,et al.  Reconstruction of high contrast images for dynamic scenes , 2011, The Visual Computer.

[9]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[10]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[11]  Stefanos Zafeiriou,et al.  Robust FFT-Based Scale-Invariant Image Registration with Image Gradients , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Hiroshi Nagahashi,et al.  Cross-Parameterization for Triangular Meshes with Semantic Features , 2007 .

[13]  Frédo Durand,et al.  Noise-optimal capture for high dynamic range photography , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Dani Lischinski,et al.  Colorization using optimization , 2004, ACM Trans. Graph..

[15]  Jan Kautz,et al.  Exposure Fusion , 2007, 15th Pacific Conference on Computer Graphics and Applications (PG'07).

[16]  Hans-Peter Seidel,et al.  Optimal HDR reconstruction with linear digital cameras , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Adam Finkelstein,et al.  The Generalized PatchMatch Correspondence Algorithm , 2010, ECCV.

[18]  Wai-kuen Cham,et al.  Reference-guided exposure fusion in dynamic scenes , 2012, J. Vis. Commun. Image Represent..

[19]  Marius Tico,et al.  Artifact-free High Dynamic Range imaging , 2009, 2009 IEEE International Conference on Computational Photography (ICCP).

[20]  Tae-Hyun Oh,et al.  Robust High Dynamic Range Imaging by Rank Minimization , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Manuel M. Oliveira,et al.  Domain transform for edge-aware image and video processing , 2011, SIGGRAPH 2011.