Deep Rectangling for Image Stitching: A Learning Baseline
- URL: http://arxiv.org/abs/2203.03831v1
- Date: Tue, 8 Mar 2022 03:34:10 GMT
- Title: Deep Rectangling for Image Stitching: A Learning Baseline
- Authors: Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu, Yao Zhao
- Abstract summary: We build the first image stitching rectangling dataset with a large diversity in irregular boundaries and scenes.
Experiments demonstrate our superiority over traditional methods both quantitatively and qualitatively.
- Score: 57.76737888499145
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Stitched images provide a wide field-of-view (FoV) but suffer from unpleasant
irregular boundaries. To deal with this problem, existing image rectangling
methods devote to searching an initial mesh and optimizing a target mesh to
form the mesh deformation in two stages. Then rectangular images can be
generated by warping stitched images. However, these solutions only work for
images with rich linear structures, leading to noticeable distortions for
portraits and landscapes with non-linear objects. In this paper, we address
these issues by proposing the first deep learning solution to image
rectangling. Concretely, we predefine a rigid target mesh and only estimate an
initial mesh to form the mesh deformation, contributing to a compact one-stage
solution. The initial mesh is predicted using a fully convolutional network
with a residual progressive regression strategy. To obtain results with high
content fidelity, a comprehensive objective function is proposed to
simultaneously encourage the boundary rectangular, mesh shape-preserving, and
content perceptually natural. Besides, we build the first image stitching
rectangling dataset with a large diversity in irregular boundaries and scenes.
Experiments demonstrate our superiority over traditional methods both
quantitatively and qualitatively.
Related papers
- PRS: Sharp Feature Priors for Resolution-Free Surface Remeshing [30.28380889862059]
We present a data-driven approach for automatic feature detection and remeshing.
Our algorithm improves over state-of-the-art by 26% normals F-score and 42% perceptual $textRMSE_textv$.
arXiv Detail & Related papers (2023-11-30T12:15:45Z) - 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) - RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline
Model and DoF-based Curriculum Learning [62.86400614141706]
We propose a new learning model, i.e., Rectangling Rectification Network (RecRecNet)
Our model can flexibly warp the source structure to the target domain and achieves an end-to-end unsupervised deformation.
Experiments show the superiority of our solution over the compared methods on both quantitative and qualitative evaluations.
arXiv Detail & Related papers (2023-01-04T15:12:57Z) - Deformable Surface Reconstruction via Riemannian Metric Preservation [9.74575494970697]
Estimating the pose of an object from a monocular image is an inverse problem fundamental in computer vision.
This paper presents an approach to inferring continuous deformable surfaces from a sequence of images.
arXiv Detail & Related papers (2022-12-22T10:45:08Z) - Efficient Textured Mesh Recovery from Multiple Views with Differentiable
Rendering [8.264851594332677]
We propose an efficient coarse-to-fine approach to recover the textured mesh from multi-view images.
We optimize the shape geometry by minimizing the difference between the rendered mesh with the depth predicted by the learning-based multi-view stereo algorithm.
In contrast to the implicit neural representation on shape and color, we introduce a physically based inverse rendering scheme to jointly estimate the lighting and reflectance of the objects.
arXiv Detail & Related papers (2022-05-25T03:33:55Z) - Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images [82.32776379815712]
We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses.
We adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network.
Our model is robust to the quality of the initial mesh and the error of camera pose, and can be combined with a differentiable function for test-time optimization.
arXiv Detail & Related papers (2022-04-21T03:42:31Z) - Spatial-Separated Curve Rendering Network for Efficient and
High-Resolution Image Harmonization [59.19214040221055]
We propose a novel spatial-separated curve rendering network (S$2$CRNet) for efficient and high-resolution image harmonization.
The proposed method reduces more than 90% parameters compared with previous methods.
Our method can work smoothly on higher resolution images in real-time which is more than 10$times$ faster than the existing methods.
arXiv Detail & Related papers (2021-09-13T07:20:16Z) - Z2P: Instant Rendering of Point Clouds [104.1186026323896]
We present a technique for rendering point clouds using a neural network.
Existing point rendering techniques either use splatting, or first reconstruct a surface mesh that can then be rendered.
arXiv Detail & Related papers (2021-05-30T13:58:24Z) - Practical Wide-Angle Portraits Correction with Deep Structured Models [17.62752136436382]
This paper introduces the first deep learning based approach to remove perspective distortions from photos.
Given a wide-angle portrait as input, we build a cascaded network consisting of a LineNet, a ShapeNet, and a transition module.
For the quantitative evaluation, we introduce two novel metrics, line consistency and face congruence.
arXiv Detail & Related papers (2021-04-26T10:47:35Z)
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.