Abstract
We present a novel algorithm for view synthesis that utilizes a soft 3D reconstruction to improve quality, continuity and robustness. Our main contribution is the formulation of a soft 3D representation that preserves depth uncertainty through each stage of 3D reconstruction and rendering. We show that this representation is beneficial throughout the view synthesis pipeline. During view synthesis, it provides a soft model of scene geometry that provides continuity across synthesized views and robustness to depth uncertainty. During 3D reconstruction, the same robust estimates of scene visibility can be applied iteratively to improve depth estimation around object edges. Our algorithm is based entirely on O(1) filters, making it conducive to acceleration and it works with structured or unstructured sets of input views. We compare with recent classical and learning-based algorithms on plenoptic lightfields, wide baseline captures, and lightfield videos produced from camera arrays.
- Robert Anderson, David Gallup, Jonathan T. Barron, Janne Kontkanen, Noah Snavely, Carlos Hernández, Sameer Agarwal, and Steven M. Seitz. 2016. Jump: Virtual Reality Video. ACM Trans. Graph. 35, 6, Article 198 (Nov. 2016), 198:1--198:13 pages. Google ScholarDigital Library
- Chris Buehler, Michael Bosse, Leonard McMillan, Steven Gortler, and Michael Cohen. 2001. Unstructured Lumigraph Rendering. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '01). ACM, New York, NY, USA, 425--432. Google ScholarDigital Library
- Brian K Cabral. 2016. Introducing Facebook Surround 360: An open, high-quality 3D-360 video capture system. (2016). https://code.facebook.com/posts/1755691291326688Google Scholar
- Gaurav Chaurasia, Sylvain Duchene, Sorkine-Hornung, and Olga Drettakis George. 2013. Depth Synthesis and Local Warps for Plausible Image-based Navigation. ACM Trans. Graph. 32, 3, Article 30 (July 2013), 30:1--30:12 pages. Google ScholarDigital Library
- Gaurav Chaurasia, Olga Sorkine-Hornung, and George Drettakis. 2011. Silhouette-Aware Warping for Image-Based Rendering. Computer Graphics Forum 30, 4 (2011). Google ScholarDigital Library
- Shenchang Eric Chen and Lance Williams. 1993. View Interpolation for Image Synthesis. In Proceedings of the 20th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '93). ACM, 279--288. Google ScholarDigital Library
- Paul E. Debevec. 1996. Modeling and Rendering Architecture from Photographs. Ph.D. Dissertation. University of California at Berkeley, Computer Science Division, Berkeley CA. Google ScholarDigital Library
- Pedro F. Felzenszwalb and Daniel P. Huttenlocher. 2006. Efficient Belief Propagation for Early Vision. Int. J. Comput. Vision 70, 1 (Oct. 2006), 41--54. Google ScholarDigital Library
- John Flynn, Ivan Neulander, James Philbin, and Noah Snavely. 2016. DeepStereo: Learning to Predict New Views From the World's Imagery. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
- Yasutaka Furukawa and Carlos Hernández. 2015. Multi-View Stereo: A Tutorial. Foundations and Trends in Computer Graphics and Vision 9, 1--2 (2015), 1--148. Google ScholarDigital Library
- Yoav HaCohen, Eli Shechtman, Dan B. Goldman, and Dani Lischinski. 2011. Nonrigid Dense Correspondence with Applications for Image Enhancement. In ACM SIGGRAPH 2011 Papers (SIGGRAPH '11). ACM, New York, NY, USA, Article 70, 70:1--70:10 pages. Google ScholarDigital Library
- Samuel W. Hasinoff, Sing Bing Kang, and Richard Szeliski. 2006. Boundary matting for view synthesis. Computer Vision and Image Understanding 103, 1 (2006), 22--32. Google ScholarDigital Library
- Kaiming He, Jian Sun, and Xiaoou Tang. 2010. Guided Image Filtering. In Proceedings of the 11th European Conference on Computer Vision: Part I (ECCV'10). Springer-Verlag, Berlin, Heidelberg, 1--14.Google ScholarDigital Library
- Asmaa Hosni, Michael Bleyer, Christoph Rhemann, Margrit Gelautz, and Carsten Rother. 2011. Real-time Local Stereo Matching Using Guided Image Filtering. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2011). 1--6. Vortrag: IEEE International Conference on Multimedia and Expo (ICME), Barcelona, Spain; 2011-07-11 -- 2011-07-15. Google ScholarDigital Library
- Hae-Gon Jeon, Jaesik Park, Gyeongmin Choe, Jinsun Park, Yunsu Bok, Yu-Wing Tai, and In So Kweon. 2015. Accurate Depth Map Estimation From a Lenslet Light Field Camera. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google ScholarCross Ref
- Nima Khademi Kalantari, Ting-Chun Wang, and Ravi Ramamoorthi. 2016. Learning-Based View Synthesis for Light Field Cameras. ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2016) 35, 6 (2016). Google ScholarDigital Library
- Sing Bing Kang, Richard Szeliski, and Jinxiang Chai. 2001. Handling Occlusions in Dense Multi-view Stereo. In CVPR (1). IEEE Computer Society, 103--110.Google Scholar
- V. Kolmogorov and R. Zabih. 2001. Computing visual correspondence with occlusions using graph cuts. In Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, Vol. 2. 508--515 vol.2.Google ScholarCross Ref
- Johannes Kopf, Fabian Langguth, Daniel Scharstein, Richard Szeliski, and Michael Goesele. 2013. Image-based Rendering in the Gradient Domain. ACM Trans. Graph. 32, 6, Article 199 (Nov. 2013), 199:1--199:9 pages. Google ScholarDigital Library
- Tom Lokovic and Eric Veach. 2000. Deep Shadow Maps. In Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '00). ACM Press/Addison-Wesley Publishing Co., New York, NY, USA, 385--392. Google ScholarDigital Library
- Jiangbo Lu, Hongsheng Yang, Dongbo Min, and Minh N. Do. 2013. Patch Match Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation. In Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR '13). IEEE Computer Society, Washington, DC, USA, 1854--1861. Google ScholarDigital Library
- Ziyang Ma, Kaiming He, Yichen Wei, Jian Sun, and Enhua Wu. 2013. Constant Time Weighted Median Filtering for Stereo Matching and Beyond. In Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV '13). IEEE Computer Society, Washington, DC, USA, 49--56. Google ScholarDigital Library
- Leonard McMillan and Gary Bishop. 1995. Plenoptic Modeling: An Image-based Rendering System. In Proceedings of the 22Nd Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '95). ACM, New York, NY, USA, 39--46. Google ScholarDigital Library
- William T. Reeves, David H. Salesin, and Robert L. Cook. 1987. Rendering Antialiased Shadows with Depth Maps. In Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH '87). ACM, New York, NY, USA, 283--291. Google ScholarDigital Library
- Sudipta Sinha, Drew Steedly, and Rick Szeliski. 2009. Piecewise Planar Stereo for Image-based Rendering, In Twelfth IEEE International Conference on Computer Vision (ICCV 2009).Google ScholarCross Ref
- Sudipta N. Sinha, Johannes Kopf, Michael Goesele, Daniel Scharstein, and Richard Szeliski. 2012. Image-based Rendering for Scenes with Reflections. ACM Trans. Graph. 31, 4, Article 100 (July 2012), 100:1--100:10 pages. Google ScholarDigital Library
- Noah Snavely, Steven M. Seitz, and Richard Szeliski. 2006. Photo Tourism: Exploring Photo Collections in 3D. In ACM SIGGRAPH 2006 Papers (SIGGRAPH '06). ACM, New York, NY, USA, 835--846. Google ScholarDigital Library
- C. Strecha, R. Fransens, and L. Van Gool. 2004. Wide-baseline stereo from multiple views: A probabilistic account. In Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., Vol. 1. I-552-I-559 Vol.1.Google Scholar
- Jian Sun, Nan-Ning Zheng, and Heung-Yeung Shum. 2003. Stereo Matching Using Belief Propagation. IEEE Trans. Pattern Anal. Mach. Intell. 25, 7 (July 2003), 787--800. Google ScholarDigital Library
- Rick Szeliski and Polina Golland. 1999. Stereo Matching with Transparency and Matting. International Journal of Computer Vision 32/1 (May 1999), 45âĂŞ61. Google ScholarDigital Library
- Michael W. Tao, Sunil Hadap, Jitendra Malik, and Ravi Ramamoorthi. 2013. Depth from Combining Defocus and Correspondence Using light-Field Cameras. International Conference on Computer Vision (ICCV). Google ScholarDigital Library
- Ting-Chun Wang, Alexei Efros, and Ravi Ramamoorthi. 2015. Occlusion-aware depth estimation using light-field cameras. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). Google ScholarDigital Library
- Zhou Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. 2004. Image Quality Assessment: From Error Visibility to Structural Similarity. Trans. Img. Proc. 13, 4 (April 2004), 600--612. Google ScholarDigital Library
- Sven Wanner and Bastian Goldluecke. 2014. Variational light field analysis for disparity estimation and super-resolution. 36 (2014), 606--619. Google ScholarDigital Library
- F. L. Zhang, J. Wang, E. Shechtman, Z. Y. Zhou, J. X. Shi, and S. M. Hu. 2016. PlenoPatch: Patch-based Plenoptic Image Manipulation. IEEE Transactions on Visualization and Computer Graphics PP, 99 (2016), 1--1. Google ScholarDigital Library
- Enliang Zheng, Enrique Dunn, Vladimir Jojic, and Jan-Michael Frahm. 2014. PatchMatch Based Joint View Selection and Depthmap Estimation. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Google ScholarDigital Library
Index Terms
- Soft 3D reconstruction for view synthesis
Recommendations
Photo-Consistent Reconstruction of Semitransparent Scenes by Density-Sheet Decomposition
This paper considers the problem of reconstructing visually realistic 3D models of dynamic semitransparent scenes, such as fire, from a very small set of simultaneous views (even two). We show that this problem is equivalent to a severely ...
Single-View View Synthesis with Self-rectified Pseudo-Stereo
AbstractSynthesizing novel views from a single view image is a highly ill-posed problem. We discover an effective solution to reduce the learning ambiguity by expanding the single-view view synthesis problem to a multi-view setting. Specifically, we ...
High-quality virtual view synthesis in 3DTV and FTV
Autostereoscopic 3DTV is becoming an exciting media that enable us to view a 3D scene from more than one viewpoint. Meanwhile, considered as the ultimate autostereoscopic 3DTV, Free-viewpoint TV (FTV) can provide arbitrary views by freely synthesizing ...
Comments