# Spatial-Angular Attention Network for Light Field Reconstruction

arXiv: https://arxiv.org/abs/2007.02252 · HTML: https://mlsanity.com/paper/2007.02252/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [Disentangling Light Fields for Super-Resolution and Disparity Estimation](https://mlsanity.com/paper/2202.10603/) (2022)
- [Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution](https://mlsanity.com/paper/2302.08058/) (2023)
- [Real-World Light Field Image Super-Resolution via Degradation Modulation](https://mlsanity.com/paper/2206.06214/) (2022)
- [Light Field Implicit Representation for Flexible Resolution Reconstruction](https://mlsanity.com/paper/2112.00185/) (2021)
- [Beyond Subspace Isolation: Many-to-Many Transformer for Light Field Image Super-resolution](https://mlsanity.com/paper/2401.00740/) (2024)
- [RealLiFe: Real-Time Light Field Reconstruction via Hierarchical Sparse Gradient Descent](https://mlsanity.com/paper/2307.03017/) (2023)
- [OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation](https://mlsanity.com/paper/2307.15588/) (2023)
- [MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolution](https://mlsanity.com/paper/2410.06478/) (2024)
- [Physics-Informed Ensemble Representation for Light-Field Image Super-Resolution](https://mlsanity.com/paper/2305.20006/) (2023)

## Abstract (arXiv)

Typical learning-based light field reconstruction methods demand in constructing a large receptive field by deepening the network to capture correspondences between input views. In this paper, we propose a spatial-angular attention network to perceive correspondences in the light field non-locally, and reconstruction high angular resolution light field in an end-to-end manner. Motivated by the non-local attention mechanism, a spatial-angular attention module specifically for the high-dimensional light field data is introduced to compute the responses from all the positions in the epipolar plane for each pixel in the light field, and generate an attention map that captures correspondences along the angular dimension. We then propose a multi-scale reconstruction structure to efficiently implement the non-local attention in the low spatial scale, while also preserving the high frequency components in the high spatial scales. Extensive experiments demonstrate the superior performance of the proposed spatial-angular attention network for reconstructing sparsely-sampled light fields with non-Lambertian effects.