Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping

• URL: http://arxiv.org/abs/2406.19922v1
• Date: Fri, 28 Jun 2024 13:51:59 GMT
• Title: Parallax-tolerant Image Stitching via Segmentation-guided Multi-homography Warping
• Authors: Tianli Liao, Ce Wang, Lei Li, Guangen Liu, Nan Li,
• Abstract summary: We propose a novel image stitching method using multi-homography warping guided by image segmentation. Our method provides the best alignment accuracy by a large margin, compared with the state-of-the-art methods.
• Score: 14.098118907921947
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large parallax between images is an intractable issue in image stitching. Various warping-based methods are proposed to address it, yet the results are unsatisfactory. In this paper, we propose a novel image stitching method using multi-homography warping guided by image segmentation. Specifically, we leverage the Segment Anything Model to segment the target image into numerous contents and partition the feature points into multiple subsets via the energy-based multi-homography fitting algorithm. The multiple subsets of feature points are used to calculate the corresponding multiple homographies. For each segmented content in the overlapping region, we select its best-fitting homography with the lowest photometric error. For each segmented content in the non-overlapping region, we calculate a weighted combination of the linearized homographies. Finally, the target image is warped via the best-fitting homographies to align with the reference image, and the final panorama is generated via linear blending. Comprehensive experimental results on the public datasets demonstrate that our method provides the best alignment accuracy by a large margin, compared with the state-of-the-art methods. The source code is available at https://github.com/tlliao/multi-homo-warp.

Related papers

• RecDiffusion: Rectangling for Image Stitching with Diffusion Models [53.824503710254206]
  We introduce a novel diffusion-based learning framework, textbfRecDiffusion, for image stitching rectangling. This framework combines Motion Diffusion Models (MDM) to generate motion fields, effectively transitioning from the stitched image's irregular borders to a geometrically corrected intermediary.
  arXiv  Detail & Related papers  (2024-03-28T06:22:45Z)
• OsmLocator: locating overlapping scatter marks with a non-training generative perspective [48.50108853199417]
  Locating overlapping marks faces many difficulties such as no texture, less contextual information, hallow shape and tiny size. Here, we formulate it as a optimization problem on clustering-based re-visualization from a non-training generative perspective. We especially built a dataset named 2023 containing hundreds of scatter images with different markers and various levels of overlapping severity, and tested the proposed method and compared it to existing methods.
  arXiv  Detail & Related papers  (2023-12-18T12:39:48Z)
• Generative Powers of Ten [60.6740997942711]
  We present a method that uses a text-to-image model to generate consistent content across multiple image scales. We achieve this through a joint multi-scale diffusion sampling approach. Our method enables deeper levels of zoom than traditional super-resolution methods.
  arXiv  Detail & Related papers  (2023-12-04T18:59:25Z)
• Variational multichannel multiclass segmentation using unsupervised lifting with CNNs [0.0]
  We implement a flexible multiclass segmentation method that divides a given image into $K$ different regions. We use convolutional neural networks (CNNs) targeting a pre-decomposition of the image. Special emphasis is given to the extraction of informative feature maps serving as a starting point for the segmentation.
  arXiv  Detail & Related papers  (2023-02-04T18:01:47Z)
• Multiscale Analysis for Improving Texture Classification [62.226224120400026]
  This paper employs the Gaussian-Laplacian pyramid to treat different spatial frequency bands of a texture separately. We aggregate features extracted from gray and color texture images using bio-inspired texture descriptors, information-theoretic measures, gray-level co-occurrence matrix features, and Haralick statistical features into a single feature vector.
  arXiv  Detail & Related papers  (2022-04-21T01:32:22Z)
• Image Processing Methods for Coronal Hole Segmentation, Matching, and Map Classification [0.0]
  The goal is to use physical models to predict geomagnetic storms. We decompose the problem into three subproblems: (i) coronal hole segmentation based on physical constraints, (ii) matching clusters of coronal holes between different maps, and (iii) physical map classification. The proposed multi-modal segmentation method significantly outperformed SegNet, U-net, Henney-Harvey, and FCN by providing accurate boundary detection.
  arXiv  Detail & Related papers  (2022-01-04T23:19:53Z)
• BoundarySqueeze: Image Segmentation as Boundary Squeezing [104.43159799559464]
  We propose a novel method for fine-grained high-quality image segmentation of both objects and scenes. Inspired by dilation and erosion from morphological image processing techniques, we treat the pixel level segmentation problems as squeezing object boundary. Our method yields large gains on COCO, Cityscapes, for both instance and semantic segmentation and outperforms previous state-of-the-art PointRend in both accuracy and speed under the same setting.
  arXiv  Detail & Related papers  (2021-05-25T04:58:51Z)
• A Novel Falling-Ball Algorithm for Image Segmentation [0.14337588659482517]
  Region-based Falling-Ball algorithm is presented, which is a region-based segmentation algorithm. The proposed algorithm detects the catchment basins by assuming that a ball falling from hilly terrains will stop in a catchment basin.
  arXiv  Detail & Related papers  (2021-05-06T12:41:10Z)
• TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations [35.9576572490994]
  We propose TransFill, a multi-homography transformed fusion method to fill the hole by referring to another source image that shares scene contents with the target image. We learn to adjust the color and apply a pixel-level warping to each homography-warped source image to make it more consistent with the target. Our method achieves state-of-the-art performance on pairs of images across a variety of wide baselines and color differences, and generalizes to user-provided image pairs.
  arXiv  Detail & Related papers  (2021-03-29T22:45:07Z)
• Rethinking Interactive Image Segmentation: Feature Space Annotation [68.8204255655161]
  We propose interactive and simultaneous segment annotation from multiple images guided by feature space projection. We show that our approach can surpass the accuracy of state-of-the-art methods in foreground segmentation datasets.
  arXiv  Detail & Related papers  (2021-01-12T10:13:35Z)
• Spectral Image Segmentation with Global Appearance Modeling [0.913755431537592]
  We introduce a new spectral method for image segmentation that incorporates long range relationships for global appearance modeling. The approach combines two different graphs, one is a sparse graph that captures spatial relationships between nearby pixels and another is a dense graph that captures pairwise similarity between all pairs of pixels.
  arXiv  Detail & Related papers  (2020-06-11T16:21:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.