Research map / 3D vision / Depth and stereo
Learning Depth from Focus in the Wild
Changyeon Won, Hae-Gon Jeon
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add alignment network (ablation) | depth-from-focus network · Rendered focal stacks | MAE: 0.0247 -> 0.0151 | Improved |
| use learned alignment instead of initial FoV warping (ablation) | depth-from-focus network · Rendered focal stacks | MAE: 0.0165 -> 0.0151 | Improved |
| use alignment network instead of homography (ablation) | depth-from-focus network · Rendered focal stacks | inference time (s): 0.8708 -> 0.0923 | Improved |
| use alignment network instead of homography (ablation) | depth-from-focus network · Rendered focal stacks | MAE: 0.0151 -> 0.0151 | No clear effect |
| use SRD instead of 2D ResNet block (ablation) | depth-from-focus network · DefocusNet dataset | MAE: 0.0421 -> 0.0403 | Improved |
| use SRD instead of 3D ResNet block (ablation) | depth-from-focus network · DefocusNet dataset | MAE: 0.0409 -> 0.0403 | Improved |
| use EFD instead of max-pooling + 3D Conv (ablation) | depth-from-focus network · DefocusNet dataset | MAE: 0.0421 -> 0.0403 | Improved |
| use EFD instead of strided conv (ablation) | depth-from-focus network · DefocusNet dataset | MAE: 0.0419 -> 0.0403 | Improved |
| use EFD instead of 3D pooling layer (ablation) | depth-from-focus network · DefocusNet dataset | MAE: 0.0414 -> 0.0403 | Improved |
| train with random number of focal slices instead of fixed five (ablation) | depth-from-focus network · DefocusNet dataset | depth error | Improved |
| proposed network vs AiFDepthNet | depth-from-focus network · DDFF 12-Scene | delta<1.25 accuracy: 68.33 -> 77.96 | Improved |
| proposed network vs AiFDepthNet, cross-dataset | depth-from-focus network · Middlebury (trained on FlyingThings3D) | MAE: 3.825 -> 1.645 | Improved |
Closest papers by meaning
- Deep Depth from Focal Stack with Defocus Model for Camera-Setting Invariance (IJCV 2023 · similarity 0.91)
- Bridging Unsupervised and Supervised Depth From Focus via All-in-Focus Supervision (ICCV 2021 · similarity 0.91)
- Single Image Depth Estimation Trained via Depth From Defocus Cues (CVPR 2019 · similarity 0.90)
- Defocus Blur Detection via Depth Distillation (ECCV 2020 · similarity 0.90)
- DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints (NeurIPS 2025 · similarity 0.88)
- Multi-Focus Image Fusion via Explicit Defocus Blur Modelling (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
