# Unsupervised Light Field Depth Estimation via Multi-view Feature Matching with Occlusion Prediction

arXiv: https://arxiv.org/abs/2301.08433 · HTML: https://mlsanity.com/paper/2301.08433/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 63 references that are in the map.
- First posted on arXiv 20 Jan 2023.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [Light Field Neural Rendering](https://mlsanity.com/paper/2112.09687/) (2021)
- [Learning to Synthesize a 4D RGBD Light Field from a Single Image](https://mlsanity.com/paper/1708.03292/) (2017)
- [EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images](https://mlsanity.com/paper/1804.02379/) (2018)
- [Occlusion-Aware Cost Constructor for Light Field Depth Estimation](https://mlsanity.com/paper/2203.01576/) (2022)
- [High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction](https://mlsanity.com/paper/1910.01426/) (2019)
- [Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions](https://mlsanity.com/paper/1708.01964/) (2017)
- [Learning Light Field Angular Super-Resolution via a Geometry-Aware Network](https://mlsanity.com/paper/2002.11263/) (2020)
- [Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields](https://mlsanity.com/paper/2106.03043/) (2021)
- [LRT: An Efficient Low-Light Restoration Transformer for Dark Light Field Images](https://mlsanity.com/paper/2209.02197/) (2022)

## Built on by (most cited first, 3 of 3)

- [OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimation](https://mlsanity.com/paper/2305.17710/) (2023)
- [RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions](https://mlsanity.com/paper/2509.19165/) (2025)
- [Iterative Occlusion-Aware Light Field Depth Estimation using 4D Geometrical Cues](https://mlsanity.com/paper/2403.02043/) (2024)

## Abstract (arXiv)

Depth estimation from light field (LF) images is a fundamental step for numerous applications. Recently, learning-based methods have achieved higher accuracy and efficiency than the traditional methods. However, it is costly to obtain sufficient depth labels for supervised training. In this paper, we propose an unsupervised framework to estimate depth from LF images. First, we design a disparity estimation network (DispNet) with a coarse-to-fine structure to predict disparity maps from different view combinations. It explicitly performs multi-view feature matching to learn the correspondences effectively. As occlusions may cause the violation of photo-consistency, we introduce an occlusion prediction network (OccNet) to predict the occlusion maps, which are used as the element-wise weights of photometric loss to solve the occlusion issue and assist the disparity learning. With the disparity maps estimated by multiple input combinations, we then propose a disparity fusion strategy based on the estimated errors with effective occlusion handling to obtain the final disparity map with higher accuracy. Experimental results demonstrate that our method achieves superior performance on both the dense and sparse LF images, and also shows better robustness and generalization on the real-world LF images compared to the other methods.