AI Paper Atlas

Research map / 3D vision / Depth and stereo

ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data

Haojie Zhao, Junsong Chen, Lijun Wang, Huchuan Lu

CVPR 2023 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 22 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
Fine-tune the RGB tracker on ARKitTrack training data using RGB channels (ablation)OSTrack · ARKitTrack-VOTF-score: 0.441 -> 0.443Improved
Fine-tune the RGB tracker on DepthTrack training data using RGB channels (ablation)OSTrack · DepthTrackF-score: 0.567 -> 0.574Improved
Use BEV features without cross-view fusion (ablation)Fine-tuned OSTrack · ARKitTrack-VOTF-score: 0.443 -> 0.423Hurt
Use BEV features without cross-view fusion (ablation)Fine-tuned OSTrack · DepthTrackF-score: 0.574 -> 0.553Hurt
Add BEV geometry and cross-view fusion (ablation)Fine-tuned OSTrack · ARKitTrack-VOTF-score: 0.443 -> 0.470Improved
Add BEV geometry and cross-view fusion (ablation)Fine-tuned OSTrack · DepthTrackF-score: 0.574 -> 0.602Improved
Model depth for each pixel with a Gaussian distribution centered on its input depth (ablation)BEV transformation with cross-view fusion · ARKitTrack-VOTF-score: 0.470 -> 0.479Improved
Model depth for each pixel with a Gaussian distribution centered on its input depth (ablation)BEV transformation with cross-view fusion · DepthTrackF-score: 0.602 -> 0.612Improved
Use one dynamic template updated every N frames (ablation)VOS baseline without dynamic templates · ARKitTrack-VOSJ&F: 0.630 -> 0.642Improved
Use IoU prediction to control updates to one template (ablation)VOS model with ONE · ARKitTrack-VOSJ&F: 0.642 -> 0.648Improved
Use IoU prediction to control adding templates to the memory bank (ablation)VOS model · ARKitTrack-VOSJ&F: 0.648 -> 0.662Improved
Train and evaluate on the diverse ARKitTrack benchmark rather than existing RGB-D benchmarksRGB-D trackers · ARKitTrack-VOTF-scoreMixed

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