# Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision

arXiv: https://arxiv.org/abs/2108.10843 · HTML: https://mlsanity.com/paper/2108.10843/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 24 Aug 2021.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs](https://mlsanity.com/paper/1712.07384/) (2017)
- [Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1604.03650/) (2016)
- [Synthetic Depth-of-Field with a Single-Camera Mobile Phone](https://mlsanity.com/paper/1806.04171/) (2018)
- [Single Image Depth Estimation Trained via Depth from Defocus Cues](https://mlsanity.com/paper/2001.05036/) (2020)
- [360SD-Net: 360deg Stereo Depth Estimation with Learnable Cost Volume](https://mlsanity.com/paper/1911.04460/) (2019)
- [Focus on defocus: bridging the synthetic to real domain gap for depth estimation](https://mlsanity.com/paper/2005.09623/) (2020)
- [Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization](https://mlsanity.com/paper/2004.02215/) (2020)
- [Deep Depth From Focus](https://mlsanity.com/paper/1704.01085/) (2017)
- [Learning to Autofocus](https://mlsanity.com/paper/2004.12260/) (2020)
- [The Visual Centrifuge: Model-Free Layered Video Representations](https://mlsanity.com/paper/1812.01461/) (2018)
- [Aperture Supervision for Monocular Depth Estimation](https://mlsanity.com/paper/1711.07933/) (2017)
- [LiFF: Light Field Features in Scale and Depth](https://mlsanity.com/paper/1901.03916/) (2019)
- [Variational Depth from Focus Reconstruction](https://mlsanity.com/paper/1408.0173/) (2014)
- [Video Depth-From-Defocus](https://mlsanity.com/paper/1610.03782/) (2016)

## Built on by (most cited first, 23 of 23)

- [Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation](https://mlsanity.com/paper/2406.12849/) (2024)
- [Deep Depth from Focus with Differential Focus Volume](https://mlsanity.com/paper/2112.01712/) (2021)
- [Fully Self-Supervised Depth Estimation from Defocus Clue](https://mlsanity.com/paper/2303.10752/) (2023)
- [Aberration-Aware Depth-from-Focus](https://mlsanity.com/paper/2303.04654/) (2023)
- [HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors](https://mlsanity.com/paper/2407.18443/) (2024)
- [Learning Depth from Focus in the Wild](https://mlsanity.com/paper/2207.09658/) (2022)
- [Deep Depth from Focal Stack with Defocus Model for Camera-Setting Invariance](https://mlsanity.com/paper/2202.13055/) (2022)
- [Camera-Independent Single Image Depth Estimation from Defocus Blur](https://mlsanity.com/paper/2311.13045/) (2023)
- [Efficient Depth- and Spatially-Varying Image Simulation for Defocus Deblur](https://mlsanity.com/paper/2507.00372/) (2025)
- [Generative Refocusing: Flexible Defocus Control from a Single Image](https://mlsanity.com/paper/2512.16923/) (2025)
- [Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus](https://mlsanity.com/paper/2409.12323/) (2024)
- [Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues](https://mlsanity.com/paper/2505.17358/) (2025)
- [Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus](https://mlsanity.com/paper/2402.18175/) (2024)
- [BuFF: Burst Feature Finder for Light-Constrained 3D Reconstruction](https://mlsanity.com/paper/2209.09470/) (2022)
- [FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack](https://mlsanity.com/paper/2310.11178/) (2023)
- [Learning Monocular Depth from Focus with Event Focal Stack](https://mlsanity.com/paper/2405.06944/) (2024)
- [Fovea Stacking: Imaging with Dynamic Localized Aberration Correction](https://mlsanity.com/paper/2506.00716/) (2025)
- [DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints](https://mlsanity.com/paper/2509.21992/) (2025)
- [Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Network](https://mlsanity.com/paper/2512.10498/) (2025)
- [Generative Multi-Focus Image Fusion](https://mlsanity.com/paper/2512.21495/) (2025)
- [Depth from Defocus via Direct Optimization](https://mlsanity.com/paper/2602.18509/) (2026)
- [Zero-Shot Depth from Defocus](https://mlsanity.com/paper/2603.26658/) (2026)
- [Towards Minimal Focal Stack in Shape from Focus](https://mlsanity.com/paper/2604.01603/) (2026)

## Abstract (arXiv)

Depth estimation is a long-lasting yet important task in computer vision. Most of the previous works try to estimate depth from input images and assume images are all-in-focus (AiF), which is less common in real-world applications. On the other hand, a few works take defocus blur into account and consider it as another cue for depth estimation. In this paper, we propose a method to estimate not only a depth map but an AiF image from a set of images with different focus positions (known as a focal stack). We design a shared architecture to exploit the relationship between depth and AiF estimation. As a result, the proposed method can be trained either supervisedly with ground truth depth, or unsupervisedly with AiF images as supervisory signals. We show in various experiments that our method outperforms the state-of-the-art methods both quantitatively and qualitatively, and also has higher efficiency in inference time.