Learning Texture Transformer Network for Light Field Super-Resolution
- URL: http://arxiv.org/abs/2210.09293v1
- Date: Sun, 9 Oct 2022 15:16:07 GMT
- Title: Learning Texture Transformer Network for Light Field Super-Resolution
- Authors: Javeria Shabbir, M. Zeshan Alam, M. Umair Mukati
- Abstract summary: We propose a method to improve the spatial resolution of light field images with the aid of the Transformer Network (TTSR)
The results demonstrate around 4 dB to 6 dB PSNR gain over a bicubically resized light field image.
- Score: 1.5469452301122173
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Hand-held light field cameras suffer from low spatial resolution due to the
inherent spatio-angular tradeoff. In this paper, we propose a method to improve
the spatial resolution of light field images with the aid of the Texture
Transformer Network (TTSR). The proposed method consists of three modules: the
first module produces an all-in focus high-resolution perspective image which
serves as a reference image for the second module, i.e. TTSR, which in turn
produces a high-resolution light field. The last module refines the spatial
resolution by imposing a light field prior. The results demonstrate around 4 dB
to 6 dB PSNR gain over a bicubically resized light field image
Related papers
- Mamba-based Light Field Super-Resolution with Efficient Subspace Scanning [48.99361249764921]
Transformer-based methods have demonstrated impressive performance in 4D light field (LF) super-resolution.
However, their quadratic complexity hinders the efficient processing of high resolution 4D inputs.
We propose a Mamba-based Light Field Super-Resolution method, named MLFSR, by designing an efficient subspace scanning strategy.
arXiv Detail & Related papers (2024-06-23T11:28:08Z) - Light Field Spatial Resolution Enhancement Framework [0.24578723416255746]
We propose a novel light field framework for resolution enhancement.
The first module generates a high-resolution, all-in-focus image.
The second module, a texture transformer network, enhances the resolution of each light field perspective independently.
arXiv Detail & Related papers (2024-05-05T02:07:10Z) - Unsupervised Learning of High-resolution Light Field Imaging via Beam
Splitter-based Hybrid Lenses [42.5604477188514]
We design a beam splitter-based hybrid light field imaging prototype to record 4D light field image and high-resolution 2D image simultaneously.
The 2D image could be considered as the high-resolution ground truth corresponding to the low-resolution central sub-aperture image of 4D light field image.
We propose an unsupervised learning-based super-resolution framework with the hybrid light field dataset.
arXiv Detail & Related papers (2024-02-29T10:30:02Z) - Passive superresolution imaging of incoherent objects [63.942632088208505]
Method consists of measuring the field's spatial mode components in the image plane in the overcomplete basis of Hermite-Gaussian modes and their superpositions.
Deep neural network is used to reconstruct the object from these measurements.
arXiv Detail & Related papers (2023-04-19T15:53:09Z) - Sub-Aperture Feature Adaptation in Single Image Super-resolution Model
for Light Field Imaging [17.721259583120396]
This paper proposes an adaptation module in a pretrained Single Image Super Resolution (SISR) network to leverage the powerful SISR model.
It is an adaptation in the SISR network to further exploit the spatial and angular information in LF images to improve the super resolution performance.
arXiv Detail & Related papers (2022-07-25T03:43:56Z) - 3DVSR: 3D EPI Volume-based Approach for Angular and Spatial Light field
Image Super-resolution [2.127049691404299]
This paper presents a learning-based approach applied to 3D epipolar image (EPI) to reconstruct high-resolution light field.
An extensive evaluation on 90 challenging synthetic and real-world light field scenes from 7 published datasets shows that the proposed approach outperforms state-of-the-art methods.
arXiv Detail & Related papers (2022-01-04T18:57:00Z) - Light Field Reconstruction Using Convolutional Network on EPI and
Extended Applications [78.63280020581662]
A novel convolutional neural network (CNN)-based framework is developed for light field reconstruction from a sparse set of views.
We demonstrate the high performance and robustness of the proposed framework compared with state-of-the-art algorithms.
arXiv Detail & Related papers (2021-03-24T08:16:32Z) - Hyperspectral Image Super-resolution via Deep Progressive Zero-centric
Residual Learning [62.52242684874278]
Cross-modality distribution of spatial and spectral information makes the problem challenging.
We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net.
Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
arXiv Detail & Related papers (2020-06-18T06:32:11Z) - Learning Light Field Angular Super-Resolution via a Geometry-Aware
Network [101.59693839475783]
We propose an end-to-end learning-based approach aiming at angularly super-resolving a sparsely-sampled light field with a large baseline.
Our method improves the PSNR of the second best method up to 2 dB in average, while saves the execution time 48$times$.
arXiv Detail & Related papers (2020-02-26T02:36:57Z) - Learned Multi-View Texture Super-Resolution [76.82725815863711]
We present a super-resolution method capable of creating a high-resolution texture map for a virtual 3D object from a set of lower-resolution images of that object.
Our architecture unifies the concepts of (i) multi-view super-resolution based on the redundancy of overlapping views and (ii) single-view super-resolution based on a learned prior of high-resolution (HR) image structure.
arXiv Detail & Related papers (2020-01-14T13:49:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.