AI Paper Atlas

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

Transformation-Equivariant 3D Object Detection for Autonomous Driving

Hai Wu, Chenglu Wen, Wei Li, Xin Li, Ruigang Yang, Cheng Wang

AAAI 2023 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 144 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 transformation-equivariant TED-S instead of Voxel-RCNNVoxel-RCNN · KITTI valCar 3D AP (R40), Moderate: 85.29 -> 87.91Improved
Use transformation-equivariant TED-M instead of multi-modal SFDmulti-modal detector · KITTI valCar 3D AP (R40), Moderate: 88.27 -> 88.94Improved
Use TED-M instead of SFDmulti-modal detector · KITTI testCar 3D AP (R40), Moderate: 84.76 -> 85.28Improved
Use TED-S instead of PV-RCNN++LiDAR-only detector · Waymo valVehicle mAP (L2): 70.26 -> 70.50Improved
Add DA-Aug (ablation)Voxel-RCNN · KITTI valCar 3D AP: 85.29 -> 85.72Improved
Replace SpConv with TeSpConv and add TeBEV pooling (ablation)Voxel-RCNN + DA-Aug · KITTI valCar 3D AP: 85.72 -> 86.33Improved
Add TiVoxel pooling (ablation)TeSpConv + DA-Aug + TeBEV pooling · KITTI valCar 3D AP: 86.33 -> 87.91Improved
Use 1 rotation instead of 3 (ablation)TED-S · KITTI valCar 3D AP: 87.91 -> 85.73Hurt
Use 2 rotations instead of 3 (ablation)TED-S · KITTI valCar 3D AP: 87.91 -> 87.13Hurt
Increase rotation count from 3 to 4 (ablation)TED-S · KITTI valCar 3D AP: 87.91 -> 87.95No clear effect
Increase rotation count from 3 to 4 (ablation)TED-M · KITTI valCar 3D AP: 88.94 -> 88.89Hurt
Replace single-pass detection with TTA (ablation)Voxel-RCNN with DA-Aug · KITTI valCar 3D AP, Moderate: 85.72 -> 86.65Improved

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