Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Title of host publication | 2021 IEEE/CVF International Conference on Computer Vision ICCV 2021 |
Subtitle of host publication | Proceedings |
Publisher | Institute of Electrical and Electronics Engineers, Inc. |
Pages | 2430-2439 |
ISBN (electronic) | 978-1-6654-2812-5 |
ISBN (print) | 978-1-6654-2813-2 |
Publication status | Published - Oct 2021 |
Publication series
Name | International Conference on Computer Vision (ICCV) |
---|---|
ISSN (Print) | 1550-5499 |
ISSN (electronic) | 2380-7504 |
Conference
Title | IEEE International Conference on Computer Vision 2021 |
---|---|
Location | Virtual |
Period | 11 - 17 October 2021 |
Link(s)
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. The source code is publicly available at https://github.com/MantangGuo/DI4SLF.
Citation Format(s)
Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines. / Guo, Mantang; Jin, Jing; Liu, Hui et al.
2021 IEEE/CVF International Conference on Computer Vision ICCV 2021: Proceedings. Institute of Electrical and Electronics Engineers, Inc., 2021. p. 2430-2439 (International Conference on Computer Vision (ICCV)).
2021 IEEE/CVF International Conference on Computer Vision ICCV 2021: Proceedings. Institute of Electrical and Electronics Engineers, Inc., 2021. p. 2430-2439 (International Conference on Computer Vision (ICCV)).
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review