# OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation

arXiv: https://arxiv.org/abs/2203.02231 · HTML: https://mlsanity.com/paper/2203.02231/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 51 references that are in the map.
- First posted on arXiv 4 Mar 2022.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2011.02910/) (2020)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [What Matters in Unsupervised Optical Flow](https://mlsanity.com/paper/2006.04902/) (2020)
- [EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images](https://mlsanity.com/paper/1804.02379/) (2018)
- [Occlusion-aware Unsupervised Learning of Depth from 4-D Light Fields](https://mlsanity.com/paper/2106.03043/) (2021)

## Built on by (most cited first, 7 of 7)

- [Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention](https://mlsanity.com/paper/2405.11616/) (2024)
- [Align3R: Aligned Monocular Depth Estimation for Dynamic Videos](https://mlsanity.com/paper/2412.03079/) (2024)
- [Iterative approach to reconstructing neural disparity fields from light-field data](https://mlsanity.com/paper/2407.15380/) (2024)
- [V2V3D: View-to-View Denoised 3D Reconstruction for Light-Field Microscopy](https://mlsanity.com/paper/2504.07853/) (2025)
- [PNR: Physics-informed Neural Representation for high-resolution LFM reconstruction](https://mlsanity.com/paper/2409.18223/) (2024)
- [Monocular Depth Guided Occlusion-Aware Disparity Refinement via Semi-supervised Learning in Laparoscopic Images](https://mlsanity.com/paper/2505.08178/) (2025)
- [Frequency-Structured Field Learning for Light-Field Disparity Estimation](https://mlsanity.com/paper/2607.14941/) (2026)

## Abstract (arXiv)

Light field disparity estimation is an essential task in computer vision with various applications. Although supervised learning-based methods have achieved both higher accuracy and efficiency than traditional optimization-based methods, the dependency on ground-truth disparity for training limits the overall generalization performance not to say for real-world scenarios where the ground-truth disparity is hard to capture. In this paper, we argue that unsupervised methods can achieve comparable accuracy, but, more importantly, much higher generalization capacity and efficiency than supervised methods. Specifically, we present the Occlusion Pattern Aware Loss, named OPAL, which successfully extracts and encodes the general occlusion patterns inherent in the light field for loss calculation. OPAL enables: i) accurate and robust estimation by effectively handling occlusions without using any ground-truth information for training and ii) much efficient performance by significantly reducing the network parameters required for accurate inference. Besides, a transformer-based network and a refinement module are proposed for achieving even more accurate results. Extensive experiments demonstrate our method not only significantly improves the accuracy compared with the SOTA unsupervised methods, but also possesses strong generalization capacity, even for real-world data, compared with supervised methods. Our code will be made publicly available.