Please use this identifier to cite or link to this item: https://repository.cihe.edu.hk/jspui/handle/cihe/4118
Title: Learning dynamic interpolation for extremely sparse light fields with wide baselines
Author(s): Liu, Hui 
Author(s): Guo, M.
Jin, J.
Hou, J.
Issue Date: 2021
Publisher: IEEE
Related Publication(s): Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2021
Start page: 2450
End page: 2459
Abstract: 
In this paper, we tackle the problem of dense light field (LF) reconstruction from sparsely-sampled ones with wide baselines and propose a learnable model, namely dynamic interpolation, to replace the commonly-used geometry warping operation. Specifically, with the estimated geometric relation between input views, we first construct a lightweight neural network to dynamically learn weights for interpolating neighbouring pixels from input views to synthesize each pixel of novel views independently. In contrast to the fixed and content-independent weights employed in the geometry warping operation, the learned interpolation weights implicitly incorporate the correspondences between the source and novel views and adapt to different image content information. Then, we recover the spatial correlation between the independently synthesized pixels of each novel view by referring to that of input views using a geometry-based spatial refinement module. We also constrain the angular correlation between the novel views through a disparity-oriented LF structure loss. Experimental results on LF datasets with wide baselines show that the reconstructed LFs achieve much higher PSNR/SSIM and preserve the LF parallax structure better than state-of-the-art methods.
URI: https://repository.cihe.edu.hk/jspui/handle/cihe/4118
CIHE Affiliated Publication: No
Appears in Collections:CIS Publication

Files in This Item:
File Description SizeFormat
View Online200 BHTMLView/Open
SFX Query Show full item record

Google ScholarTM

Check


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