Vanishing Point Guided Natural Image Stitching
- URL: http://arxiv.org/abs/2004.02478v1
- Date: Mon, 6 Apr 2020 08:29:40 GMT
- Title: Vanishing Point Guided Natural Image Stitching
- Authors: Kai Chen, Jian Yao, Jingmin Tu, Yahui Liu, Yinxuan Li and Li Li
- Abstract summary: We propose a novel natural image stitching method, which takes into account the guidance of vanishing points to tackle the mentioned failures.
Inspired by a vital observation that mutually vanishing points in Manhattan world can provide useful orientation clues, we design a scheme to effectively estimate prior of image similarity.
Our method achieves state-of-the-art performance in both quantitative and qualitative experiments on natural image stitching.
- Score: 13.307030394454216
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, works on improving the naturalness of stitching images gain more
and more extensive attention. Previous methods suffer the failures of severe
projective distortion and unnatural rotation, especially when the number of
involved images is large or images cover a very wide field of view. In this
paper, we propose a novel natural image stitching method, which takes into
account the guidance of vanishing points to tackle the mentioned failures.
Inspired by a vital observation that mutually orthogonal vanishing points in
Manhattan world can provide really useful orientation clues, we design a scheme
to effectively estimate prior of image similarity. Given such estimated prior
as global similarity constraints, we feed it into a popular mesh deformation
framework to achieve impressive natural stitching performances. Compared with
other existing methods, including APAP, SPHP, AANAP, and GSP, our method
achieves state-of-the-art performance in both quantitative and qualitative
experiments on natural image stitching.
Related papers
- Combining Generative and Geometry Priors for Wide-Angle Portrait Correction [54.448014761978975]
We propose encapsulating the generative face prior as a guided natural manifold to facilitate the correction of facial regions.
A notable central symmetry relationship exists in the non-face background, yet it has not been explored in the correction process.
This geometry prior motivates us to introduce a novel constraint to explicitly enforce symmetry throughout the correction process.
arXiv Detail & Related papers (2024-10-13T16:36:52Z) - Assessing Image Inpainting via Re-Inpainting Self-Consistency Evaluation [46.974439781041774]
We introduce an innovative evaluation paradigm that utilizes a self-supervised metric based on multiple re-inpainting passes.
This approach emphasizes the principle of self-consistency to enable the exploration of various viable inpainting solutions.
arXiv Detail & Related papers (2024-05-25T15:05:08Z) - Towards Robust Image Stitching: An Adaptive Resistance Learning against
Compatible Attacks [66.98297584796391]
Image stitching seamlessly integrates images captured from varying perspectives into a single wide field-of-view image.
Given a pair of captured images, subtle perturbations and distortions which go unnoticed by the human visual system tend to attack the correspondence matching.
This paper presents the first attempt to improve the robustness of image stitching against adversarial attacks.
arXiv Detail & Related papers (2024-02-25T02:36:33Z) - Implicit Neural Image Stitching [41.28311406845525]
We propose a novel approach, implicit Neural Image Stitching (NIS) that extends arbitrary-scale super-resolution.
Our method estimates Fourier coefficients of images for quality-enhancing warps.
Our experiments show that our approach achieves improvement in resolving the low-definition imaging of the previous deep image stitching.
arXiv Detail & Related papers (2023-09-04T07:40:30Z) - Deep Image Matting: A Comprehensive Survey [85.77905619102802]
This paper presents a review of recent advancements in image matting in the era of deep learning.
We focus on two fundamental sub-tasks: auxiliary input-based image matting and automatic image matting.
We discuss relevant applications of image matting and highlight existing challenges and potential opportunities for future research.
arXiv Detail & Related papers (2023-04-10T15:48:55Z) - Parallax-Tolerant Unsupervised Deep Image Stitching [57.76737888499145]
We propose UDIS++, a parallax-tolerant unsupervised deep image stitching technique.
First, we propose a robust and flexible warp to model the image registration from global homography to local thin-plate spline motion.
To further eliminate the parallax artifacts, we propose to composite the stitched image seamlessly by unsupervised learning for seam-driven composition masks.
arXiv Detail & Related papers (2023-02-16T10:40:55Z) - ViCE: Self-Supervised Visual Concept Embeddings as Contextual and Pixel
Appearance Invariant Semantic Representations [77.3590853897664]
This work presents a self-supervised method to learn dense semantically rich visual embeddings for images inspired by methods for learning word embeddings in NLP.
arXiv Detail & Related papers (2021-11-24T12:27:30Z) - Single View Geocentric Pose in the Wild [18.08385304935249]
We present a model for learning to regress geocentric pose using airborne lidar images.
We also address practical issues required to deploy this method in the wild for real-world applications.
arXiv Detail & Related papers (2021-05-18T01:55:15Z) - Bridging Composite and Real: Towards End-to-end Deep Image Matting [88.79857806542006]
We study the roles of semantics and details for image matting.
We propose a novel Glance and Focus Matting network (GFM), which employs a shared encoder and two separate decoders.
Comprehensive empirical studies have demonstrated that GFM outperforms state-of-the-art methods.
arXiv Detail & Related papers (2020-10-30T10:57:13Z)
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.