AI Paper Atlas

Research map / Point clouds / Segmentation and detection

DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Tao Ma, Xuemeng Yang, Hongbin Zhou, Xin Li, Botian Shi, Junjie Liu, Yuchen Yang, Zhizheng Liu, Liang He, Yu Qiao, Yikang Li, Hongsheng Li

ICCV 2023 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 49 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 attribute-based refining modules (geometry, position, confidence) on top of upstream tracks (ablation)DetZero · WOD val VehicleAPH L2: 75.24 -> 82.92Improved
add geometry refining model (ablation)DetZero upstream · WOD val Vehicle IoU=0.73D APH L1: 82.57 -> 84.49Improved
add position refining model (ablation)DetZero upstream · WOD val Vehicle IoU=0.73D APH L1: 82.57 -> 85.48Improved
add confidence refining model (ablation)DetZero GRM+PRM · WOD val Vehicle IoU=0.73D APH L1: 87.81 -> 89.06Improved
add offline tracker over baseline tracker in the detection pipeline (ablation)DetZero upstream · WOD val Vehicle IoU=0.73D APH L1: 82.57 -> 82.57No clear effect
use own offline tracker instead of baseline tracker (ablation)DetZero · WOD val VehicleRecall@track: 23.96 -> 40.28Improved
replace SOTA trackers with the proposed offline tracker (ablation)DetZero · WOD val Vehicle3D APH: 80.56 -> 82.92 (vs ImmortalTracker)Improved
use attribute-based refiner instead of 3DAL refiner (ablation)DetZero with baseline tracker · WOD val Vehicle3D APH L2: 76.33 -> 78.14Improved
train student on 10% human + 90% DetZero auto labels versus 10% human onlyCenterPoint student · WOD VehicleAPH: 66.28 -> 73.91Improved
train student on 90% DetZero labels only versus 100% human labelsCenterPoint student · WOD PedestrianAPH: 71.16 -> 71.39Improved
apply refining module to lower quality upstream detections (ablation)DetZero refiner · WOD val VehicleAPH L2: 70.00 -> 74.68Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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