Research map / 3D vision / Depth and stereo
A second-order theory of texture for depth from focus
Sreekar Ranganathan, Ioannis Gkioulekas
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 a narrowband spectral filter (10-100 nm) in front of the lens (ablation) | depth from focus on textureless scenes · ambient indoor and outdoor scenes | fraction of unrecovered pixels | Improved |
| narrow the filter bandwidth with exposure increased to compensate (ablation) | DFF · real scenes | depth reconstruction quality | Improved |
| use 10 nm filter with only 4x exposure increase (3 stops underexposed) (ablation) | DFF · weakly textured patch | z-score / contrast: 4x exposure instead of 32x | Improved |
| illuminate with a large nearby ring light instead of a spot light (ablation) | filtered DFF · controlled LED scene | DFF improvement from filter | Hurt |
| move LED from 60 cm to 20 cm (ablation) | filtered DFF · LED distance experiment | in-focus contrast and DFF performance: 60 cm -> 20 cm | Hurt |
| apply filter on strongly translucent material (wax) versus opaque (ablation) | filtered DFF · mixed-material scene | DFF improvement | Mixed |
| use pixel-adaptive aggregation with the filter | filtered DFF · real scenes | lateral resolution | Improved |
| set f-number away from optimum (too large or too small) (ablation) | filtered DFF · indoor textureless patch | second-order texture contrast | Hurt |
Closest papers by meaning
- Coherence As Texture - Passive Textureless 3D Reconstruction by Self-interference (CVPR 2024 · similarity 0.87)
- Neural Microfacet Fields for Inverse Rendering (ICCV 2023 · similarity 0.84)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.83)
- Depth Sensing by Near-Infrared Light Absorption in Water (TPAMI 2020 · similarity 0.83)
- Eclipse: Disambiguating Illumination and Materials using Unintended Shadows (CVPR 2024 · similarity 0.82)
- Subsurface Scattering for Gaussian Splatting (NeurIPS 2024 · similarity 0.82)
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.
