AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Revisiting 3D Object Detection From an Egocentric Perspective

Boyang Deng, Charles R. Qi, Mahyar Najibi, Thomas Funkhouser, Yin Zhou, Dragomir Anguelov

NeurIPS 2021 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 9 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 StarPoly contour instead of detector boxPV-RCNN detections · Waymo val range [0m, 5m)mSDE: 0.107 -> 0.063Improved
use StarPoly contour instead of detector boxPV-RCNN detections · Waymo val range [20m, 40m)mSDE: 0.207 -> 0.152Improved
use convex visible contour instead of detector box (ablation)PV-RCNN detections · Waymo val range [20m, 40m)mSDE: 0.207 -> 0.266Hurt
use convex visible contour instead of detector box (ablation)PV-RCNN detections · Waymo val range [0m, 5m)mSDE: 0.107 -> 0.090Improved
evaluate with SDE instead of IoU to separate true and false collision predictionsPV-RCNN · Waymo val collision detectionmean metric gap: 0.114 vs 0.162Improved
rank detectors by SDE-APD instead of IoU-APdetectors · Waymo valranking: PointPillars 0.817 vs PV-RCNN 0.808Mixed

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