ABSTRACT
We present a method to adjust the disparity of stereoscopic 3D (S3D) images non-uniformly to improve viewing comfort or to allow artistic license with depth after capture. Using disparity maps, our method decomposes the input S3D image into layers where adjustments are performed. Since adjusting the disparity potentially introduces holes where previously occluded regions become visible, we also present a disparity-aware inpainting method to fill these holes. We test our method using raytraced S3D images with ground truth disparity maps to demonstrate that our method produces close-to-ideal results. Finally, we discuss how we used our method to adjust the disparity of several S3D photos used in the WWI documentary "Soldiers' Stories".
- C. Barnes, E. Shechtman, A. Finkelstein, and D. B. Goldman. PatchMatch: A randomized correspondence algorithm for structural image editing. ACM Trans. Graph., 28(3):24:1--24:11, July 2009. Google ScholarDigital Library
- M. Bertalmìo, A. Bertozzi, and G. Sapiro. Navier-Stokes, fluid dynamics, and image and video inpainting. In Computer Vision and Pattern Recognition, volume 1, 2001.Google ScholarCross Ref
- H. Furihata, T. Yendo, M. Panahpour Tehrani, T. Fujii, and M. Tanimoto. Novel view synthesis with residual error feedback for FTV, 2010.Google ScholarCross Ref
- H. Hirschmuller. Stereo processing by semiglobal matching and mutual information. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2):328--341, Feb 2008. Google ScholarDigital Library
- G. R. Jones, D. Lee, N. S. Holliman, and D. Ezra. Controlling perceived depth in stereoscopic images, 2001.Google Scholar
- Dir.. J. Kitzen. Soldiers' Stories. Kallisti Media, 2014.Google Scholar
- M. T. M. Lambooij, W. A. IJsselsteijn, M. Fortuin, and I. Heynderickx. Visual discomfort and visual fatigue of stereoscopic displays: A review. Journal of Imaging Science and Technology, 53(3):030201:1--14, May/June 2009.Google ScholarCross Ref
- M. Lang, A. Hornung, O. Wang, S. Poulakos, A. Smolic, and M. Gross. Nonlinear disparity mapping for stereoscopic 3D. SIGGRAPH '10, New York, NY, USA, 2010. ACM. Google ScholarDigital Library
- N. Manap and J. Soraghan. Novel view synthesis based on depth map layers representation. In 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video, pages 1--4, 2011.Google Scholar
- N. Manap, J. Soraghan, and L. Petropoulakis. Depth image layers separation (DILS) algorithm of image view synthesis based on stereo vision. In Signal and Image Processing Applications (ICSIPA), pages 61--66, 2013.Google ScholarCross Ref
- B. Mendiburu. 3D Movie Making: Stereoscopic Digital Cinema from Script to Screen. Focal Press, May 2009.Google Scholar
- B. Morse, J. Howard, S. Cohen, and B. Price. PatchMatch-based content completion of stereo image pairs. In 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), 2012 Second International Conference on, pages 555--562, Oct 2012. Google ScholarDigital Library
- L. Northam, P. Asente, and C. S. Kaplan. Consistent stylization and painterly rendering of stereoscopic 3D images. In NPAR, NPAR '12, pages 47--56, Aire-la-Ville, Switzerland, Switzerland, 2012. Eurographics Association. Google ScholarDigital Library
- L. Northam, P. Asente, and C. S. Kaplan. Stereoscopic 3D image stylization. Comput. Graph., 37(5):389--402, 2013. Google ScholarDigital Library
- H. Pan, C. Yuan, and S. Daly. 3D video disparity scaling for preference and prevention of discomfort, 2011.Google ScholarCross Ref
- C. Richardt, L. Świrski, I. P. Davies, and N. A. Dodgson. Predicting stereoscopic viewing comfort using a coherence-based computational model. In Proceedings of the International Symposium on Computational Aesthetics in Graphics, Visualization, and Imaging, CAe '11, pages 97--104, New York, NY, USA, 2011. ACM. Google ScholarDigital Library
- D. Sarto. Stereoscopic supervisor Robert Neuman talks Disney 3-D. VFXWorld Magazine Online, apr 2012.Google Scholar
- D. Scharstein and C. Pal. Learning conditional random fields for stereo. In Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on, pages 1--8, June 2007.Google ScholarCross Ref
- A. Telea. An image inpainting technique based on the fast marching method. J. Graphics, GPU, and Game Tools, 9(1):23--34, 2004.Google Scholar
- L. Wang, H. Jin, R. Yang, and M. Gong. Stereoscopic inpainting: Joint color and depth completion from stereo images. In Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pages 1--8, June 2008.Google ScholarCross Ref
- O. Wang, M. Lang, M. Frei, A. Hornung, A. Smolic, and M. Gross. Stereobrush: Interactive 2D to 3D conversion using discontinuous warps. In Proceedings of the Eighth Eurographics Symposium on Sketch-Based Interfaces and Modeling, SBIM '11, pages 47--54, 2011. Google ScholarDigital Library
Index Terms
- Layer-based disparity adjustment in stereoscopic 3D media
Recommendations
Boundary-preserving stereo matching with certain region detection and adaptive disparity adjustment
Boundary-preserving stereo matching.Initial disparity estimation based on segmentation.Classification of disparity map into certain and uncertain regions.Disparity adjustment based on certain region detection. In this paper, we propose boundary-...
Perceptual Tolerance to Stereoscopic 3D Image Distortion
An intriguing aspect of picture perception is the viewer’s tolerance to variation in viewing position, perspective, and display size. These factors are also present in stereoscopic media, where there are additional parameters associated with the camera ...
Stereo panorama acquisition and automatic image disparity adjustment for stereoscopic visualization
Image-based visualization is popular for various virtual tour applications, due to high-quality photorealism or simplicity for rendering. Stereo panorama representations of the virtual world are already a common part of this, either in small (computer ...
Comments