Robust Image Stitching with Multiple Registrations
| Autor: | Charles Herrmann, Ramin Zabih, Richard Strong Bowen, Emil Keyder, Michael Krainin, Chen Wang, Ce Liu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Pixel
Panorama business.industry Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering 02 engineering and technology Variation (game tree) Image (mathematics) Image stitching Transformation (function) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Visual artifact business Parallax |
| Zdroj: | Computer Vision – ECCV 2018 ISBN: 9783030012151 ECCV (2) |
| DOI: | 10.1007/978-3-030-01216-8_4 |
| Popis: | Panorama creation is one of the most widely deployed techniques in computer vision. In addition to industry applications such as Google Street View, it is also used by millions of consumers in smartphones and other cameras. Traditionally, the problem is decomposed into three phases: registration, which picks a single transformation of each source image to align it to the other inputs, seam finding, which selects a source image for each pixel in the final result, and blending, which fixes minor visual artifacts [1, 2]. Here, we observe that the use of a single registration often leads to errors, especially in scenes with significant depth variation or object motion. We propose instead the use of multiple registrations, permitting regions of the image at different depths to be captured with greater accuracy. MRF inference techniques naturally extend to seam finding over multiple registrations, and we show here that their energy functions can be readily modified with new terms that discourage duplication and tearing, common problems that are exacerbated by the use of multiple registrations. Our techniques are closely related to layer-based stereo [3, 4], and move image stitching closer to explicit scene modeling. Experimental evidence demonstrates that our techniques often generate significantly better panoramas when there is substantial motion or parallax. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|