Research map / 3D vision / Depth and stereo
Spatially-Varying Autofocus
Yingsi Qin, Aswin C. Sankaranarayanan, Matthew O'Toole
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 |
|---|---|---|---|
| use phase-based instead of contrast-based autofocus for all-in-focus capture | Split-Lohmann spatially-varying autofocus · Adventure and Rainbow scenes, PSNR/SSIM vs number of photos | PSNR, SSIM | Improved |
| use autofocus search instead of a full focal stack | all-in-focus capture · Planes scene qualitative | number of photos: 10 photos (contrast), 4 photos (phase) vs 20 photos (focal stack) | Improved |
| replace focal sweep with spatially-varying autofocus | all-in-focus imaging · USAF target MTF at three depths | MTF (spatial resolution) | Improved |
| optical per-pixel focusing instead of a small aperture (f/36) | Planes scene · Planes scene qualitative | sharpness | Improved |
| shift focus away from nominal plane (apply phase ramp) | Split-Lohmann lens · Prototype light throughput | light throughput: 76% of rest state at most extreme focus | Hurt |
| add segmentation into layers before optical flow in phase-based autofocus | phase-based autofocus · depth boundaries | disparity assignment | Improved |
Closest papers by meaning
- Optical Model-Driven Sharpness Mapping for Autofocus in Small Depth-of-Field and Severe Defocus Scenarios (ICCV 2025 · similarity 0.86)
- User-Instructed Disparity-aware Defocus Control (NeurIPS 2025 · similarity 0.84)
- CLDefocus: Physically Grounded Compound-Lens Defocus Blur Synthesis (ECCV 2026 · similarity 0.84)
- DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints (NeurIPS 2025 · similarity 0.83)
- Multi-Focus Image Fusion via Explicit Defocus Blur Modelling (AAAI 2025 · similarity 0.83)
- DOF-GS: Adjustable Depth-of-Field 3D Gaussian Splatting for Post-Capture Refocusing, Defocus Rendering and Blur Removal (CVPR 2025 · similarity 0.81)
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.
