# Focus on defocus: bridging the synthetic to real domain gap for depth estimation

arXiv: https://arxiv.org/abs/2005.09623 · HTML: https://mlsanity.com/paper/2005.09623/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2020.

## Built on by (most cited first, 30 of 37)

- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://mlsanity.com/paper/2108.07628/) (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)
- [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)
- [Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair](https://mlsanity.com/paper/2304.04917/) (2023)
- [Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries](https://mlsanity.com/paper/2503.23606/) (2025)
- [DERD-Net: Learning Depth from Event-based Ray Densities](https://mlsanity.com/paper/2504.15863/) (2025)
- [Continuous Cost Aggregation for Dual-Pixel Disparity Extraction](https://mlsanity.com/paper/2306.07921/) (2023)
- [Mobile AR Depth Estimation: Challenges & Prospects -- Extended Version](https://mlsanity.com/paper/2310.14437/) (2023)
- [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)
- [H-GAN: the power of GANs in your Hands](https://mlsanity.com/paper/2103.15017/) (2021)
- [DAQE: Enhancing the Quality of Compressed Images by Exploiting the Inherent Characteristic of Defocus](https://mlsanity.com/paper/2211.10984/) (2022)
- [Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus](https://mlsanity.com/paper/2402.18175/) (2024)
- [Monocular Depth Decomposition of Semi-Transparent Volume Renderings](https://mlsanity.com/paper/2206.13282/) (2022)
- [GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization](https://mlsanity.com/paper/2208.10024/) (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)
- [360 in the Wild: Dataset for Depth Prediction and View Synthesis](https://mlsanity.com/paper/2406.18898/) (2024)
- [Dense Depth from Event Focal Stack](https://mlsanity.com/paper/2412.08120/) (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)
- [Point Spread Function Estimation of Defocus](https://mlsanity.com/paper/2203.02953/) (2022)

## Abstract (arXiv)

Data-driven depth estimation methods struggle with the generalization outside their training scenes due to the immense variability of the real-world scenes. This problem can be partially addressed by utilising synthetically generated images, but closing the synthetic-real domain gap is far from trivial. In this paper, we tackle this issue by using domain invariant defocus blur as direct supervision. We leverage defocus cues by using a permutation invariant convolutional neural network that encourages the network to learn from the differences between images with a different point of focus. Our proposed network uses the defocus map as an intermediate supervisory signal. We are able to train our model completely on synthetic data and directly apply it to a wide range of real-world images. We evaluate our model on synthetic and real datasets, showing compelling generalization results and state-of-the-art depth prediction.