AI Paper Atlas

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

NeurIPS 2022 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use YOLOv4 (Darknet-53) instead of Faster-RCNN (VGG-16) as detectorSurDis benchmark detectors · SurDis test setmAP (IoU 0.5): 0.396 -> 0.427Improved
Use Faster-RCNN (VGG-16) instead of SSD (VGG-16)SurDis benchmark detectors · SurDis test setmAP (IoU 0.5): 0.241 -> 0.396Improved
Use SSD detector instead of adapted Resnet-18SurDis benchmark detectors · SurDis test setmAP (IoU 0.5): 0.156 -> 0.241Improved
Increase SAD window size up to about 9 (ablation)Block-matching disparity mapping · SurDis depth mapsdepth map quality (qualitative)Improved
Increase SAD window size beyond the optimum of 9 (ablation)Block-matching disparity mapping · SurDis depth mapsdepth map quality (qualitative)Hurt
Tune disparity range to (4, 20) (ablation)Block-matching disparity mapping · SurDis depth mapsdepth map quality (qualitative)Improved
Large uniform-intensity regions in stereo pairsBlock-matching disparity mapping · SurDis depth mapsdepth map noise (qualitative)Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy