Research map / 3D vision / Depth and stereo
Video Mirror Detection with the Motion-in-Depth Cue
Alex Warren, Ke Xu, Xin Tian, Gary K. L. Tam, Benjamin W. Wah, Rynson W. H. Lau
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 MiD-AL module to baseline (ablation) | MiD-VMD · MMD (video mirror detection) | F-beta: 0.806 -> 0.843 | Improved |
| add MiD-BD module to baseline (ablation) | MiD-VMD · MMD (video mirror detection) | F-beta: 0.806 -> 0.861 | Improved |
| add both MiD-AL and MiD-BD (ablation) | MiD-VMD · MMD (video mirror detection) | F-beta: 0.806 -> 0.884 | Improved |
| encode scene flow into 16-D instead of no encoding (128) (ablation) | MiD-AL · MMD (video mirror detection) | F-beta: 0.814 -> 0.884 | Improved |
| use 16-D instead of 8-D or 32-D encoding (ablation) | MiD-AL · MMD (video mirror detection) | IoU: 0.737 (8) / 0.736 (32) -> 0.746 | Improved |
| use 3D scene flow in MGVMD instead of 2D optical flow (ablation) | MGVMD · MMD (video mirror detection) | F-beta: 0.869 -> 0.874 (Acc 0.873 -> 0.868) | Improved |
| use MiD cue instead of motion-and-depth concatenation (DCTNet+) (ablation) | video mirror detection · MMD (video mirror detection) | F-beta: 0.827 -> 0.884 | Improved |
| add scene flow (MiD) to depth-only model (ablation) | MiD-VMD · MMD (video mirror detection) | F-beta: 0.852 -> 0.884 | Improved |
| swap depth estimator (GA-Net vs RAFT-Stereo) (ablation) | MiD-VMD · MMD (video mirror detection) | F-beta: 0.857 (GA-Net) vs 0.884; ML-Depth-Pro 0.879 and DepthAnything-V2 0.878 | Mixed |
| use MiD-VMD instead of MGVMD | video mirror detection · MMD (video mirror detection) | F-beta: 0.869 -> 0.884 | Improved |
Closest papers by meaning
- Effective Video Mirror Detection with Inconsistent Motion Cues (CVPR 2024 · similarity 0.91)
- ZOOM: Learning Video Mirror Detection with Extremely-Weak Supervision (AAAI 2024 · similarity 0.88)
- Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine (CVPR 2025 · similarity 0.86)
- MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification (ICML 2025 · similarity 0.85)
- Weakly-Supervised Mirror Detection via Scribble Annotations (AAAI 2024 · similarity 0.84)
- M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (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.
