mlsanityData to 7 Oct 2026

Learning Sub-Pixel Disparity Distribution for Light Field Depth Estimation

arXiv 2208.09688 ↗First posted 20 Aug 2022cs.CV eess.IVcited by 12

Not on the map. Why?

Abstract (arXiv)

Light field (LF) depth estimation plays a crucial role in many LF-based applications. Existing LF depth estimation methods consider depth estimation as a regression problem, where a pixel-wise L1 loss is employed to supervise the training process. However, the disparity map is only a sub-space projection (i.e., an expectation) of the disparity distribution, which is essential for models to learn. In this paper, we propose a simple yet effective method to learn the sub-pixel disparity distribution by fully utilizing the power of deep networks, especially for LF of narrow baselines. We construct the cost volume at the sub-pixel level to produce a finer disparity distribution and design an uncertainty-aware focal loss to supervise the predicted disparity distribution toward the ground truth. Extensive experimental results demonstrate the effectiveness of our method.Our method significantly outperforms recent state-of-the-art LF depth algorithms on the HCI 4D LF Benchmark in terms of all four accuracy metrics (i.e., BadPix 0.01, BadPix 0.03, BadPix 0.07, and MSE ×100). The code and model of the proposed method are available at urlhttps://github.com/chaowentao/SubFocal.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 19 of its 67 references that are in the map. First posted on arXiv 20 Aug 2022.

Builds on

19 of 67 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  3. 2017Focal Loss for Dense Object Detectioncited by 749
  4. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  5. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  6. 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 82
  7. 2018EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Imagescited by 46
  8. 2022Disentangling Light Fields for Super-Resolution and Disparity Estimationcited by 42
  9. 2020Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularizationcited by 36
  10. 2018Learning Depth from Single Images with Deep Neural Network Embedding Focal Lengthcited by 25
  11. 2022Occlusion-Aware Cost Constructor for Light Field Depth Estimationcited by 23
  12. 2019High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstructioncited by 22
7 more
  1. 2017Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regionscited by 21
  2. 2021Light Field Reconstruction Using Convolutional Network on EPI and Extended Applicationscited by 18
  3. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  4. 2021Selective Light Field Refocusing for Camera Arrays Using Bokeh Rendering and Superresolutioncited by 16
  5. 2020EPI-based Oriented Relation Networks for Light Field Depth Estimationcited by 10
  6. 2016Occlusion-Model Guided Anti-Occlusion Depth Estimation in Light Fieldcited by 6
  7. 2019Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-Shiftcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 2; 2026: 1.

12 papers.

  1. 2023D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Fieldcited by 26
  2. 2023NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Resultscited by 7
  3. 2024Beyond Subspace Isolation: Many-to-Many Transformer for Light Field Image Super-resolutioncited by 3
  4. 2023OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimationcited by 2
  5. 2024Kitchen Food Waste Image Segmentation and Classification for Compost Nutrients Estimationcited by 2
  6. 2024Iterative approach to reconstructing neural disparity fields from light-field datacited by 2
  7. 2024LGFN: Lightweight Light Field Image Super-Resolution using Local Convolution Modulation and Global Attention Feature Extractioncited by 2
  8. 2024MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolutioncited by 1
  9. 2024Iterative Occlusion-Aware Light Field Depth Estimation using 4D Geometrical Cuescited by 0
  10. 2025A Linear Fractional Transformation Model and Calibration Method for Light Field Cameracited by 0
  11. 2025Light Field Based 6DoF Tracking of Previously Unobserved Objectscited by 0
  12. 2026Frequency-Structured Field Learning for Light-Field Disparity Estimationcited by 0