Research map / Detection and segmentation / CNN features
Glass Segmentation Using Intensity and Spectral Polarization Cues
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 trichromatic polarization cues to RGB intensity (ablation) | PGSNet · RGBP-Glass testing set | IoU: 76.11 -> 81.08 | Helped |
| Add trichromatic AoLP to RGB intensity (ablation) | PGSNet · RGBP-Glass testing set | IoU: 76.11 -> 77.23 | Helped |
| Add trichromatic DoLP to RGB intensity (ablation) | PGSNet · RGBP-Glass testing set | IoU: 76.11 -> 79.73 | Helped |
| Use trichromatic rather than monochromatic polarization (ablation) | PGSNet with RGB · RGBP-Glass testing set | IoU: 79.01 -> 81.08 | Helped |
| Add spectral RGB intensity instead of grayscale intensity (ablation) | PGSNet with monochromatic polarization · RGBP-Glass testing set | IoU: 75.99 -> 79.01 | Helped |
| Add EDA to dynamically balance polarization color channels (ablation) | PGSNet · RGBP-Glass testing set | IoU: 80.23 -> 81.08 | Helped |
| Add GCG to the decoder (ablation) | PGSNet · RGBP-Glass testing set | IoU: 79.64 -> 81.08 | Helped |
| Use GCGD rather than a basic decoder (ablation) | PGSNet with DMFI · RGBP-Glass testing set | IoU: 79.18 -> 81.08 | Helped |
| Add MSDP multi-scale dependencies (ablation) | PGSNet encoder · RGBP-Glass testing set | IoU: 78.65 -> 79.18 | Helped |
| Use DMFI rather than basic feature integration (ablation) | PGSNet · RGBP-Glass testing set | IoU: 79.03 -> 81.08 | Helped |
| Use both DMFI and GCGD rather than basic counterparts (ablation) | PGSNet · RGBP-Glass testing set | IoU: 77.24 -> 81.08 | Helped |
| Use DoLP rather than AoLP as the polarization cue (ablation) | PGSNet with RGB and one trichromatic polarization cue · RGBP-Glass testing set | IoU: 77.23 -> 79.73 | Helped |
Closest papers by meaning
- Leveraging RGB-D Data with Cross-Modal Context Mining for Glass Surface Detection (AAAI 2025 · similarity 0.85)
- RGB-to-Polarization Estimation: A New Task and Benchmark Study (NeurIPS 2025 · similarity 0.85)
- Exploiting Polarized Material Cues for Robust Car Detection (AAAI 2024 · similarity 0.85)
- Multi-View Dynamic Reflection Prior for Video Glass Surface Detection (AAAI 2024 · similarity 0.84)
- Material Palette: Extraction of Materials from a Single Image (CVPR 2024 · similarity 0.83)
- Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior (CVPR 2024 · similarity 0.83)
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.