Please use this identifier to cite or link to this item:
Title: See360: Novel panoramic view interpolation
Author(s): Siu, Wan Chi 
Liu, Zhisong 
Author(s): Cani, M.-P.
Issue Date: 2022
Publisher: IEEE
Journal: IEEE Transactions on Image Processing 
Volume: 31
Start page: 1857
End page: 1869
We present See360, which is a versatile and efficient framework for 360° panoramic view interpolation using latent space viewpoint estimation. Most of the existing view rendering approaches only focus on indoor or synthetic 3D environments and render new views of small objects. In contrast, we suggest to tackle camera-centered view synthesis as a 2D affine transformation without using point clouds or depth maps, which enables an effective 360° panoramic scene exploration. Given a pair of reference images, the See360 model learns to render novel views by a proposed novel Multi-Scale Affine Transformer (MSAT), enabling the coarse-to-fine feature rendering. We also propose a Conditional Latent space AutoEncoder (C-LAE) to achieve view interpolation at any arbitrary angle. To show the versatility of our method, we introduce four training datasets, namely UrbanCity360, Archinterior360, HungHom360 and Lab360, which are collected from indoor and outdoor environments for both real and synthetic rendering. Experimental results show that the proposed method is generic enough to achieve real-time rendering of arbitrary views for all four datasets. In addition, our See360 model can be applied to view synthesis in the wild: with only a short extra training time (approximately 10 mins), and is able to render unknown real-world scenes. The superior performance of See360 opens up a promising direction for camera-centered view rendering and 360° panoramic view interpolation.
DOI: 10.1109/TIP.2022.3148819
CIHE Affiliated Publication: Yes
Appears in Collections:CIS Publication

Files in This Item:
File Description SizeFormat
View Online89 BHTMLView/Open
SFX Query Show full item record

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.