# Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks?

arXiv: https://arxiv.org/abs/1809.01567 · HTML: https://mlsanity.com/paper/1809.01567/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2018.

## Built on by (most cited first, 16 of 16)

- [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)
- [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)
- [Pix2Point: Learning Outdoor 3D Using Sparse Point Clouds and Optimal Transport](https://mlsanity.com/paper/2107.14498/) (2021)
- [WorldGen: A Large Scale Generative Simulator](https://mlsanity.com/paper/2210.00715/) (2022)
- [Depth Estimation from a Single Optical Encoded Image using a Learned Colored-Coded Aperture](https://mlsanity.com/paper/2309.08033/) (2023)
- [Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challenges](https://mlsanity.com/paper/2402.12041/) (2024)
- [Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues](https://mlsanity.com/paper/2505.17358/) (2025)
- [DASHA: Decentralized Autofocusing System with Hierarchical Agents](https://mlsanity.com/paper/2108.12842/) (2021)
- [Point Spread Function Estimation of Defocus](https://mlsanity.com/paper/2203.02953/) (2022)
- [On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks](https://mlsanity.com/paper/2208.11372/) (2022)
- [Dark Channel-Assisted Depth-from-Defocus from a Single Image](https://mlsanity.com/paper/2506.06643/) (2025)
- [Large-FOV RGBD Imaging via Structured PSF Coding in a Bio-inspired Monocentric System](https://mlsanity.com/paper/2510.25314/) (2025)
- [Depth from Defocus via Direct Optimization](https://mlsanity.com/paper/2602.18509/) (2026)

## Abstract (arXiv)

Depth estimation is of critical interest for scene understanding and accurate 3D reconstruction. Most recent approaches in depth estimation with deep learning exploit geometrical structures of standard sharp images to predict corresponding depth maps. However, cameras can also produce images with defocus blur depending on the depth of the objects and camera settings. Hence, these features may represent an important hint for learning to predict depth. In this paper, we propose a full system for single-image depth prediction in the wild using depth-from-defocus and neural networks. We carry out thorough experiments to test deep convolutional networks on real and simulated defocused images using a realistic model of blur variation with respect to depth. We also investigate the influence of blur on depth prediction observing model uncertainty with a Bayesian neural network approach. From these studies, we show that out-of-focus blur greatly improves the depth-prediction network performances. Furthermore, we transfer the ability learned on a synthetic, indoor dataset to real, indoor and outdoor images. For this purpose, we present a new dataset containing real all-focus and defocused images from a Digital Single-Lens Reflex (DSLR) camera, paired with ground truth depth maps obtained with an active 3D sensor for indoor scenes. The proposed approach is successfully validated on both this new dataset and standard ones as NYUv2 or Depth-in-the-Wild. Code and new datasets are available at https://github.com/marcelampc/d3net_depth_estimation