Research map / 3D vision / Depth and stereo
SurDis: A Surface Discontinuity Dataset for Wearable Technology to Assist Blind Navigation in Urban Environments
Kuan Yew Leong, Siew Mooi Lim
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 YOLOv4 (Darknet-53) instead of Faster-RCNN (VGG-16) as detector | SurDis benchmark detectors · SurDis test set | mAP (IoU 0.5): 0.396 -> 0.427 | Improved |
| Use Faster-RCNN (VGG-16) instead of SSD (VGG-16) | SurDis benchmark detectors · SurDis test set | mAP (IoU 0.5): 0.241 -> 0.396 | Improved |
| Use SSD detector instead of adapted Resnet-18 | SurDis benchmark detectors · SurDis test set | mAP (IoU 0.5): 0.156 -> 0.241 | Improved |
| Increase SAD window size up to about 9 (ablation) | Block-matching disparity mapping · SurDis depth maps | depth map quality (qualitative) | Improved |
| Increase SAD window size beyond the optimum of 9 (ablation) | Block-matching disparity mapping · SurDis depth maps | depth map quality (qualitative) | Hurt |
| Tune disparity range to (4, 20) (ablation) | Block-matching disparity mapping · SurDis depth maps | depth map quality (qualitative) | Improved |
| Large uniform-intensity regions in stereo pairs | Block-matching disparity mapping · SurDis depth maps | depth map noise (qualitative) | Hurt |
Closest papers by meaning
- mmWalk: Towards Multi-modal Multi-view Walking Assistance (NeurIPS 2025 · similarity 0.85)
- Text to Blind Motion (NeurIPS 2024 · similarity 0.84)
- USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset (NeurIPS 2024 · similarity 0.81)
- SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models (NeurIPS 2025 · similarity 0.81)
- HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation (CVPR 2025 · similarity 0.81)
- OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising (CVPR 2024 · 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.
