Title
Efficient Propagation Of Sparse Edits On 360 Degrees Panoramas *
Abstract
We present an efficient method to propagate sparse user edits indicated by strokes on 360 degrees panoramas. Our algorithm first projects each equirectangular pixel to its corresponding position on a 3D unit sphere, so each pixel can be characterized by a feature vector consisting of its 3D coordinates and RGB color values. We formulate edit propagation as an optimization problem that aims to satisfy the user edit con-straints while preserving the manifold structure of the image at the same time. To solve the problem using a linear system efficiently, we first construct the K-D tree structure in the feature space to cluster pixels. Then we optimize the manifold structure where both the number of nearest neighbors and their corresponding weights are determined by the feature distributions. We further apply a multiresolution strategy to speedup the edit propagation. Our method is the first to perform interactive edit propaga-tion on 360 degrees panoramas. Experiments show that our method is able to generate seam-free and visually pleasing results, and users can receive instant feedback during interactive editing. (c) 2021 Elsevier Ltd. All rights reserved.
Year
DOI
Venue
2021
10.1016/j.cag.2021.03.005
COMPUTERS & GRAPHICS-UK
Keywords
DocType
Volume
360 &#176, panoramas, Sparse strokes, Edit propagation, Manifold-preserving, Adaptive KNN
Journal
96
ISSN
Citations 
PageRank 
0097-8493
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Yun Zhang1326.60
Fang-Lue Zhang226915.60
Yu-Kun Lai3102580.48
Zhe Zhu4746.50