Dec 5, 2018 · In this paper, we propose effective and efficient end-to-end convolutional neural network models for spatially super-resolving LF images.

This paper proposes effective and efficient end-to-end convolutional neural network models for spatially super-resolving LF images with an hourglass shape, ...

Jan 30, 2019 · To fully make use of the 4D structure information of LF data in both the spatial and angular domains, we propose to use 4D convolution to ...

Light field (LF) photography is an emerging paradigm for capturing more immersive representations of the real-world.

Apart from these methods, Yeung et al. [13] proposed spatial-angular separable convolution (SAS-Conv) to approximate 4D convolution while achieving efficiency.

PyTorch implementation of TIP 2018 paper: "Light Field Spatial Super-resolution Using Deep Efficient Spatial-Angular Separable Convolution". You can find ...

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with ...

LF image super-resolution (SR), also known as LF spatial SR, aims at reconstructing high-resolution (HR) LF images from their low-resolution (LR) counterparts.

Sep 19, 2019 · Light Field Spatial Super Resolution Using Deep Efficient Spatial Angular Separable Convolution IEEE PROJECTS 2019-2020 TITLE LIST Call Us: ...

This letter presents a novel method to simultaneously up-sample both the spatial and angular resolutions of a light field image via a deep convolutional ...