# Deep Depth From Focus

arXiv: https://arxiv.org/abs/1704.01085 · HTML: https://mlsanity.com/paper/1704.01085/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2017.

## Built on by (most cited first, 28 of 28)

- [Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image](https://mlsanity.com/paper/2110.05655/) (2021)
- [Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision](https://mlsanity.com/paper/2108.10843/) (2021)
- [Deep Depth from Focus with Differential Focus Volume](https://mlsanity.com/paper/2112.01712/) (2021)
- [CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization](https://mlsanity.com/paper/2109.04527/) (2021)
- [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)
- [Depth Estimation and Image Restoration by Deep Learning from Defocused Images](https://mlsanity.com/paper/2302.10730/) (2023)
- [Camera-Independent Single Image Depth Estimation from Defocus Blur](https://mlsanity.com/paper/2311.13045/) (2023)
- [Towards Real-World Focus Stacking with Deep Learning](https://mlsanity.com/paper/2311.17846/) (2023)
- [Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues](https://mlsanity.com/paper/2505.17358/) (2025)
- [Swept-Angle Synthetic Wavelength Interferometry](https://mlsanity.com/paper/2205.10655/) (2022)
- [Passive Micron-scale Time-of-Flight with Sunlight Interferometry](https://mlsanity.com/paper/2211.10732/) (2022)
- [Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding](https://mlsanity.com/paper/2512.14028/) (2025)
- [Dynamic Fusion Network For Light Field Depth Estimation](https://mlsanity.com/paper/2104.05969/) (2021)
- [Learning Multi-modal Information for Robust Light Field Depth Estimation](https://mlsanity.com/paper/2104.05971/) (2021)
- [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)
- [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)
- [Boosting Monocular Metric Depth Estimation via Bokeh Rendering](https://mlsanity.com/paper/2512.12425/) (2025)
- [Predicting Depth from Semantic Segmentation using Game Engine Dataset](https://mlsanity.com/paper/2106.15257/) (2021)
- [Unsupervised Learning Based Focal Stack Camera Depth Estimation](https://mlsanity.com/paper/2203.07904/) (2022)
- [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)
- [Double-Helix Active Geometry: LiDAR-Anchored Multi-View Depth with Selective Abstention](https://mlsanity.com/paper/2607.02561/) (2026)

## Abstract (arXiv)

Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision. Most approaches recover the depth at each pixel based on the focal setting which exhibits maximal sharpness. Yet, it is not obvious how to reliably estimate the sharpness level, particularly in low-textured areas. In this paper, we propose `Deep Depth From Focus (DDFF)' as the first end-to-end learning approach to this problem. One of the main challenges we face is the hunger for data of deep neural networks. In order to obtain a significant amount of focal stacks with corresponding groundtruth depth, we propose to leverage a light-field camera with a co-calibrated RGB-D sensor. This allows us to digitally create focal stacks of varying sizes. Compared to existing benchmarks our dataset is 25 times larger, enabling the use of machine learning for this inverse problem. We compare our results with state-of-the-art DFF methods and we also analyze the effect of several key deep architectural components. These experiments show that our proposed method `DDFFNet' achieves state-of-the-art performance in all scenes, reducing depth error by more than 75% compared to the classical DFF methods.