Research map / Detection and segmentation / CNN features
Depth-Aware Mirror Segmentation
Haiyang Mei, Bo Dong, Wen Dong, Pieter Peers, Xin Yang, Qiang Zhang, Xiaopeng Wei
Check 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 VGG-16 instead of the standard RGB feature extractor (ablation) | PDNet · RGBD-Mirror testing set | IoU: 77.77 -> 75.31 | Hurt |
| Use ResNeXt-101 instead of the standard RGB feature extractor (ablation) | PDNet · RGBD-Mirror testing set | IoU: 77.77 -> 77.25 | Hurt |
| Use 64 channels at every depth feature-extractor stage (ablation) | PDNet · RGBD-Mirror testing set | IoU: 77.77 -> 76.00 | Hurt |
| Use VGG-16 instead of the standard depth feature extractor (ablation) | PDNet · RGBD-Mirror testing set | IoU: 77.77 -> 78.87 | Improved |
| Use ResNeXt-101 instead of the standard depth feature extractor (ablation) | PDNet · RGBD-Mirror testing set | IoU: 77.77 -> 79.31 | Improved |
| Remove the depth branch (ablation) | PDNet · RGBD-Mirror testing set | IoU: 77.77 -> 73.57 | Hurt |
| Replace depth input with grayscale RGB at test time (ablation) | PDNet · RGBD-Mirror testing set | IoU: 77.77 -> 67.14 | Hurt |
| Replace depth input with a black image at test time (ablation) | PDNet · RGBD-Mirror testing set | IoU: 77.77 -> 65.98 | Hurt |
| Remove both positioning and delineating modules (ablation) | PDNet · RGBD-Mirror testing set | IoU: 70.08 -> 77.77 | Hurt |
| Add the discontinuity perception branch (ablation) | PDNet base model B · RGBD-Mirror testing set | IoU: 70.08 -> 73.81 | Improved |
| Add the correlation perception branch (ablation) | PDNet base model B · RGBD-Mirror testing set | IoU: 70.08 -> 72.48 | Improved |
| Add the positioning module (ablation) | PDNet base model B · RGBD-Mirror testing set | IoU: 70.08 -> 75.54 | Improved |
Closest papers by meaning
- Seeing Beyond Illusion: Generalized and Efficient Mirror Detection (AAAI 2026 · similarity 0.91)
- Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine (CVPR 2025 · similarity 0.86)
- ZOOM: Learning Video Mirror Detection with Extremely-Weak Supervision (AAAI 2024 · similarity 0.85)
- Effective Video Mirror Detection with Inconsistent Motion Cues (CVPR 2024 · similarity 0.84)
- MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification (ICML 2025 · similarity 0.84)
- MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World (CVPR 2025 · similarity 0.84)
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.
