Gradient-based image fusion for HDR creation in dynamic scenes

In this paper we will tackle the problem of HDR image generation for dynamic scenes. The current techniques assume the scene to be static in order to create the radiance map. Otherwise, strong artifacts appear. Some attempts have been made to extend these methods directly to dynamic scenes, but, as we will explain, an intensity fusion approach leads to spatial inconsistencies in the radiance values. We propose a gradient-based approach that avoids bleeding and ghosting, two common artifacts. Moreover the method improves the detail rendition of the original images. To support the validity of our method, results and comparisons with the state of the art will be presented.

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

[2]  Richard Szeliski,et al.  Seamless Image Stitching of Scenes with Large Motions and Exposure Differences , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  Shree K. Nayar,et al.  Radiometric self calibration , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[4]  Antonin Chambolle,et al.  A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging , 2011, Journal of Mathematical Imaging and Vision.

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

[6]  Richard Szeliski,et al.  High dynamic range video , 2003, ACM Trans. Graph..

[7]  Gemma Piella,et al.  Image Fusion for Enhanced Visualization: A Variational Approach , 2009, International Journal of Computer Vision.

[8]  Hans-Peter Seidel,et al.  Background estimation from non-time sequence images , 2008, Graphics Interface.

[9]  Jitendra Malik,et al.  Recovering high dynamic range radiance maps from photographs , 1997, SIGGRAPH.

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

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

[12]  Shree K. Nayar,et al.  Modeling the space of camera response functions , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Edoardo Provenzi,et al.  An Analysis of Visual Adaptation and Contrast Perception for Tone Mapping , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[15]  Sang Uk Lee,et al.  Ghost-Free High Dynamic Range Imaging , 2010, ACCV.

[16]  Shree K. Nayar,et al.  Determining the Camera Response from Images: What Is Knowable? , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

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

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

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

[20]  Sylvain Paris,et al.  Error-Tolerant Image Compositing , 2010, ECCV.

[21]  Erik Reinhard,et al.  Ghost Removal in High Dynamic Range Images , 2006, 2006 International Conference on Image Processing.

[22]  Steve Mann,et al.  ON BEING `UNDIGITAL' WITH DIGITAL CAMERAS: EXTENDING DYNAMIC RANGE BY COMBINING DIFFERENTLY EXPOSED PICTURES , 1995 .

[23]  Zeev Farbman,et al.  Interactive local adjustment of tonal values , 2006, ACM Trans. Graph..

[24]  J. Shewchuk.  An Introduction to the Conjugate Gradient Method Without the Agonizing Pain , 1994 .