High dynamic range imaging for dynamic scenes via locality-constrained low-rank matrix completion

High dynamic range (HDR) imaging expands the capabilities of a camera by synthesizing a sequence of different exposure images. However, due to camera and object motion, ghosts exist in the synthesized HDR image. The low-rank matrix completion (LRMC) model has achieved some success in ghost-free HDR imaging, but leads to artifacts around the observation region edges for neglecting local image structure. In this paper, a locality-constrained LRMC (LcLRMC) model is proposed, in which we iteratively update the background irradiance and the observation region based on the result from previous iteration. Specifically, the proposed method incorporates global and local structures. Experimental results show that compared to the conventional LRMC model, the proposed method effectively eliminates artifacts around the observation region edges.

[1]  Subhasis Chaudhuri,et al.  Bottom-up segmentation for ghost-free reconstruction of a dynamic scene from multi-exposure images , 2010, ICVGIP '10.

[2]  Anna Tomaszewska,et al.  Image Registration for Multi-exposure High Dynamic Range Image Acquisition , 2007 .

[3]  Erik Reinhard,et al.  High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting , 2010 .

[4]  Wei Zhang,et al.  Motion-free exposure fusion based on inter-consistency and intra-consistency , 2017, Inf. Sci..

[5]  Wolfgang Heidrich,et al.  HDR-VDP-2: a calibrated visual metric for visibility and quality predictions in all luminance conditions , 2011, SIGGRAPH 2011.

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

[7]  E. Reinhard.  Photographic Tone Reproduction for Digital Images , 2002 .

[8]  Greg Ward,et al.  Automatic High-Dynamic Range Image Generation for Dynamic Scenes , 2008, IEEE Computer Graphics and Applications.

[9]  Desire Sidibé,et al.  Ghost detection and removal for high dynamic range images: Recent advances , 2012, Signal Process. Image Commun..

[10]  Arvind Ganesh,et al.  Fast algorithms for recovering a corrupted low-rank matrix , 2009, 2009 3rd IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[11]  Wai-kuen Cham,et al.  Gradient-Directed Multiexposure Composition , 2012, IEEE Transactions on Image Processing.

[12]  Lei Zhang,et al.  Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition Approach , 2017, IEEE Transactions on Image Processing.

[13]  Shanmuganathan Raman,et al.  PCA-HDR: A robust PCA based solution to HDR imaging , 2014, 2014 International Conference on Signal Processing and Communications (SPCOM).

[14]  Rafal Mantiuk,et al.  Assessment of multi-exposure HDR image deghosting methods , 2017, Comput. Graph..

[15]  Thorsten Grosch,et al.  Fast and Robust High Dynamic Range Image Generation with Camera and Object Movement , 2006 .

[16]  Hans-Peter Seidel,et al.  Dynamic range independent image quality assessment , 2008, ACM Trans. Graph..

[17]  Edmund Y. Lam,et al.  Computationally Efficient Truncated Nuclear Norm Minimization for High Dynamic Range Imaging , 2016, IEEE Transactions on Image Processing.

[18]  Zhou Wang,et al.  Multi-exposure image fusion: A patch-wise approach , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[19]  In-So Kweon,et al.  High dynamic range imaging by a rank-1 constraint , 2013, 2013 IEEE International Conference on Image Processing.

[20]  Jiebo Luo,et al.  Probabilistic Exposure Fusion , 2012, IEEE Transactions on Image Processing.

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

[22]  S. Yun,et al.  An accelerated proximal gradient algorithm for nuclear norm regularized linear least squares problems , 2009 .

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

[24]  Aykut Erdem,et al.  The State of the Art in HDR Deghosting: A Survey and Evaluation , 2015, Comput. Graph. Forum.

[25]  Chul Lee,et al.  Ghost-Free High Dynamic Range Imaging via Rank Minimization , 2014, IEEE Signal Processing Letters.

[26]  Katsushi Ikeuchi,et al.  Radiometric Calibration by Rank Minimization , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.