TL;DR
This paper introduces PIINET, a novel GAN-based method for 360-degree panoramic image inpainting that converts equirectangular images into cube maps to reduce distortion and considers the correlation between cube faces.
Contribution
The paper presents a new panoramic inpainting network that effectively handles cube map formats and face correlations, improving over existing single-image inpainting methods.
Findings
Qualitative performance surpasses existing algorithms
Utilizes cube map format to reduce distortion
Considers face correlation in the inpainting process
Abstract
Inpainting has been continuously studied in the field of computer vision. As artificial intelligence technology developed, deep learning technology was introduced in inpainting research, helping to improve performance. Currently, the input target of an inpainting algorithm using deep learning has been studied from a single image to a video. However, deep learning-based inpainting technology for panoramic images has not been actively studied. We propose a 360-degree panoramic image inpainting method using generative adversarial networks (GANs). The proposed network inputs a 360-degree equirectangular format panoramic image converts it into a cube map format, which has relatively little distortion and uses it as a training network. Since the cube map format is used, the correlation of the six sides of the cube map should be considered. Therefore, all faces of the cube map are used as…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsInpainting
