# Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications

arXiv: https://arxiv.org/abs/2103.13043 · HTML: https://mlsanity.com/paper/2103.13043/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 56 references that are in the map.
- First posted on arXiv 24 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [DeepStereo: Learning to Predict New Views from the World's Imagery](https://mlsanity.com/paper/1506.06825/) (2015)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [A 4D Light-Field Dataset and CNN Architectures for Material Recognition](https://mlsanity.com/paper/1608.06985/) (2016)

## Built on by (most cited first, 18 of 18)

- [Disentangling Light Fields for Super-Resolution and Disparity Estimation](https://mlsanity.com/paper/2202.10603/) (2022)
- [Fast Learning Radiance Fields by Shooting Much Fewer Rays](https://mlsanity.com/paper/2208.06821/) (2022)
- [Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network](https://mlsanity.com/paper/2104.06797/) (2021)
- [Learning Sub-Pixel Disparity Distribution for Light Field Depth Estimation](https://mlsanity.com/paper/2208.09688/) (2022)
- [LFSRDiff: Light Field Image Super-Resolution via Diffusion Models](https://mlsanity.com/paper/2311.16517/) (2023)
- [Light Field Depth Estimation via Stitched Epipolar Plane Images](https://mlsanity.com/paper/2203.15201/) (2022)
- [Texture-enhanced Light Field Super-resolution with Spatio-Angular Decomposition Kernels](https://mlsanity.com/paper/2111.04069/) (2021)
- [Light Field Implicit Representation for Flexible Resolution Reconstruction](https://mlsanity.com/paper/2112.00185/) (2021)
- [OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimation](https://mlsanity.com/paper/2305.17710/) (2023)
- [Efficient Light Field Reconstruction via Spatio-Angular Dense Network](https://mlsanity.com/paper/2108.03635/) (2021)
- [3DVSR: 3D EPI Volume-based Approach for Angular and Spatial Light field Image Super-resolution](https://mlsanity.com/paper/2201.01294/) (2022)
- [Geo-NI: Geometry-aware Neural Interpolation for Light Field Rendering](https://mlsanity.com/paper/2206.09736/) (2022)
- [LFIC-DRASC: Deep Light Field Image Compression Using Disentangled Representation and Asymmetrical Strip Convolution](https://mlsanity.com/paper/2409.11711/) (2024)
- [Epipolar Focus Spectrum: A Novel Light Field Representation and Application in Dense-view Reconstruction](https://mlsanity.com/paper/2204.00193/) (2022)
- [ProbNVS: Fast Novel View Synthesis with Learned Probability-Guided Sampling](https://mlsanity.com/paper/2204.03476/) (2022)
- [GAN-Based Multi-View Video Coding with Spatio-Temporal EPI Reconstruction](https://mlsanity.com/paper/2205.03599/) (2022)
- [Learning based Deep Disentangling Light Field Reconstruction and Disparity Estimation Application](https://mlsanity.com/paper/2311.08129/) (2023)
- [A Linear Fractional Transformation Model and Calibration Method for Light Field Camera](https://mlsanity.com/paper/2511.03962/) (2025)

## Abstract (arXiv)

In this paper, a novel convolutional neural network (CNN)-based framework is developed for light field reconstruction from a sparse set of views. We indicate that the reconstruction can be efficiently modeled as angular restoration on an epipolar plane image (EPI). The main problem in direct reconstruction on the EPI involves an information asymmetry between the spatial and angular dimensions, where the detailed portion in the angular dimensions is damaged by undersampling. Directly upsampling or super-resolving the light field in the angular dimensions causes ghosting effects. To suppress these ghosting effects, we contribute a novel "blur-restoration-deblur" framework. First, the "blur" step is applied to extract the low-frequency components of the light field in the spatial dimensions by convolving each EPI slice with a selected blur kernel. Then, the "restoration" step is implemented by a CNN, which is trained to restore the angular details of the EPI. Finally, we use a non-blind "deblur" operation to recover the spatial high frequencies suppressed by the EPI blur. We evaluate our approach on several datasets, including synthetic scenes, real-world scenes and challenging microscope light field data. We demonstrate the high performance and robustness of the proposed framework compared with state-of-the-art algorithms. We further show extended applications, including depth enhancement and interpolation for unstructured input. More importantly, a novel rendering approach is presented by combining the proposed framework and depth information to handle large disparities.