AI Paper Atlas

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

Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection

Lue Fan, Yuxue Yang, Yiming Mao, Feng Wang, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 39 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
add bidirectional track extension (backtracing) on top of forward-only extension (ablation)CTRL refinement · WOD val VehicleT-FN ratio: 9.1k (0.87%) -> 5.1k (0.48%)Improved
add track-centric refinement module to offline FSD (ablation)Offline FSD · WOD val Vehicle L2APH: 74.4 -> 80.1Improved
add bidirectional tracking extension before refinement (ablation)CTRL · WOD val Vehicle L2APH: 80.1 -> 81.0Improved
bidirectional tracking adds boxes without adding high-confidence false positives (ablation)CTRL · WOD val VehicleH-FP: 8.1k (0.77%) -> 8.1k (0.77%)No clear effect
do not cap input track length (use full length) (ablation)track-centric learning · WOD val Vehicle L2APH: 77.1 -> 80.1Improved
use track-centric instead of object-centric label assignment (ablation)track-centric learning · WOD val Vehicle L2APH: 79.6 -> 80.1Improved
separate static and dynamic tracks into two pipelines (ablation)track-centric learning · WOD val Vehicle L2APH: 80.1 -> 79.8No clear effect
use MIMO instead of MISO (ablation)track-centric learning · WOD val Vehicle L2APH / FPS: 79.5 -> 80.1; 1.1 -> 33.6 FPSImproved
give MISO a 4x longer training schedule (ablation)MISO · WOD val Vehicle L2APH: 79.5 -> 80.0Improved
add track coherence optimization given one GT box (ablation)CTRL · WOD val Vehicle L1 3D AP IoU=0.83D AP: 64.9 -> 76.5Improved
add track TTA (ablation)CTRL · WOD valmAP/mAPH L2: 83.6/82.1 -> 83.9/82.3Improved
replace 3DAL with CTRL for offline detectionoffline auto-labeling · WOD val Vehicle 3D AP strict3D AP: 57.8 -> 64.9Improved

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