mlsanityData to 14 Oct 2026

Deep Depth from Focus with Differential Focus Volume

arXiv 2112.01712 ↗First posted 3 Dec 2021cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Depth-from-focus (DFF) is a technique that infers depth using the focus change of a camera. In this work, we propose a convolutional neural network (CNN) to find the best-focused pixels in a focal stack and infer depth from the focus estimation. The key innovation of the network is the novel deep differential focus volume (DFV). By computing the first-order derivative with the stacked features over different focal distances, DFV is able to capture both the focus and context information for focus analysis. Besides, we also introduce a probability regression mechanism for focus estimation to handle sparsely sampled focal stacks and provide uncertainty estimation to the final prediction. Comprehensive experiments demonstrate that the proposed model achieves state-of-the-art performance on multiple datasets with good generalizability and fast speed.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 25 of its 54 references that are in the map. First posted on arXiv 3 Dec 2021.

Builds on

25 of 54 references.

References · 25

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  3. 2016Pyramid Scene Parsing Networkcited by 2,479
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  6. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  8. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  9. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  10. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  11. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  12. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
13 more
  1. 2018Pyramid Stereo Matching Networkcited by 489
  2. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 360
  3. 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
  4. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 136
  5. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  6. 2017Accurate Optical Flow via Direct Cost Volume Processingcited by 66
  7. 2020Focus on defocus: bridging the synthetic to real domain gap for depth estimationcited by 37
  8. 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
  9. 2017Deep Depth From Focuscited by 28
  10. 2018The Visual Centrifuge: Model-Free Layered Video Representationscited by 23
  11. 2021Robustness via Cross-Domain Ensemblescited by 23
  12. 2021Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervisioncited by 23
  13. 2014Variational Depth from Focus Reconstructioncited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 6; 2025: 5; 2026: 4.

20 papers.

Sort:

  1. 2023Fully Self-Supervised Depth Estimation from Defocus Cluecited by 17
  2. 2023Aberration-Aware Depth-from-Focuscited by 12
  3. 2024Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Priorcited by 12
  4. 2024HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priorscited by 11
  5. 2022Deep Depth from Focal Stack with Defocus Model for Camera-Setting Invariancecited by 7
  6. 2023Camera-Independent Single Image Depth Estimation from Defocus Blurcited by 5
  7. 2025Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundariescited by 4
  8. 2024Depth Estimation Based on 3D Gaussian Splatting Siamese Defocuscited by 3
  9. 2024Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocuscited by 2
  10. 2023FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stackcited by 1
  11. 2024Learning Monocular Depth from Focus with Event Focal Stackcited by 1
  12. 2024Dense Depth from Event Focal Stackcited by 1
8 more
  1. 2025One-Step Event-Driven High-Speed Autofocuscited by 1
  2. 2025DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraintscited by 1
  3. 2025Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Networkcited by 1
  4. 2025Boosting Monocular Metric Depth Estimation via Bokeh Renderingcited by 1
  5. 2026Depth from Defocus via Direct Optimizationcited by 0
  6. 2026Zero-Shot Depth from Defocuscited by 0
  7. 2026Towards Minimal Focal Stack in Shape from Focuscited by 0
  8. 2026Enhancing Hazy Wildlife Imagery: AnimalHaze3k and IncepDehazeGancited by 0