Alignment and mosaicing of non-overlapping images

Image alignment and mosaicing are usually performed on a set of overlapping images, using features in the area of overlap for alignment and for seamless stitching. Without image overlap current methods are helpless, and this is the case we address in this paper. So if a traveler wants to create a panoramic mosaic of a scene from pictures he has taken, but realizes back home that his pictures do not overlap, there is still hope. The proposed process has three stages: (i) Images are extrapolated beyond their original boundaries, hoping that the extrapolated areas will cover the gaps between them. This extrapolation becomes more blurred as we move away from the original image. (ii) The extrapolated images are aligned and their relative positions recovered. (iii) The gaps between the images are inpainted to create a seamless mosaic image.

• Publication year

  2012

• Venue

  International Conference on Computational Photography

• Publication date

  2012-04-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICCPhot.2012.6215214
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multiscale ultrawide foveated video extrapolation

  2011influential reference
• A fully automated greedy square jigsaw puzzle solver

  2011cited by this paper
• Ultrawide Foveated Video Extrapolation

  2011cited by this paper
• A probabilistic image jigsaw puzzle solver

  2010cited by this paper
• Shift-map image editing

  2009cited by this paper
• Full-frame video stabilization with motion inpainting

  2006cited by this paper
• Region filling and object removal by exemplar-based image inpainting

  2004cited by this paper
• Object removal by exemplar-based inpainting

  2003cited by this paper
• Texture synthesis by non-parametric sampling

  1999cited by this paper
• True multi-image alignment and its application to mosaicing and lens distortion correction

  1997cited by this paper
• A Three-Frame Algorithm for Estimating Two-Component Image Motion

  1992cited by this paper
• Hierarchical Model-Based Motion Estimation

  1992cited by this paper
• Two methods of image extension

  1990cited by this paper
• A computational framework and an algorithm for the measurement of visual motion

  1987cited by this paper
• PYRAMID METHODS IN IMAGE PROCESSING.

  1984cited by this paper

• Self-Supervised Fragment Alignment With Gaps

  2023cites this paper
• Extreme Rotation Estimation using Dense Correlation Volumes

  2021cites this paper
• Javastylosis: a tool for computer-assisted chromatic and semantics based anastylosis of frescoes

  2020cites this paper
• Development of a parameterization image stitching algorithm for ultrashort throw laser MEMS projectors

  2019cites this paper
• Image mosaicing: A deeper insight

  2019cites this paper
• Solving Archaeological Puzzles

  2018cites this paper
• Leveraging Content and Context in Understanding Activities of Daily Living

  2018influential citation
• Image Mosaic Based on Pixel Subtle Variations

  2018cites this paper
• From Reassembly to Object Completion: A Complete Systems Pipeline

  2017cites this paper
• Spatio-Temporal Alignment of Non-overlapping Sequences from Independently Panning Cameras

  2017cites this paper
• Borehole image correspondence and automated alignment

  2017cites this paper
• AutoStitcher: An Automated Program for Efficient and Robust Reconstruction of Digitized Whole Histological Sections from Tissue Fragments

  2016cites this paper
• μ-Mosaicing and Thermo-Mosaicing using Image In- painting

  2014cites this paper
• BiggerPicture

  2014cites this paper
• FrameBreak: Dramatic Image Extrapolation by Guided Shift-Maps

  2013cites this paper
• "Mind the gap"

  2013cites this paper
• A 2d + 3d rich data approach to scene understanding

  2013cites this paper