AI Paper Atlas

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

Perspective-Invariant 3D Object Detection

Ao Liang, Lingdong Kong, Dongyue Lu, Youquan Liu, Jian Fang, Huaici Zhao, Wei Tsang Ooi

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 5 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 Pi3DET-Net adaptation to PV-RCNN trained on nuScenes (vehicle to quadruped)PV-RCNN · Pi3DET QuadrupedAP 3D @0.7: 33.55 -> 46.36Improved
add Pi3DET-Net adaptation versus target-only trainingPV-RCNN · nuScenes -> Pi3DET QuadrupedAP 3D @0.7: 40.24 -> 46.36Improved
add Random Platform Jitter (ablation)Voxel RCNN · Pi3DET Vehicle -> DroneAP BEV @0.7: 52.85 -> 60.20Improved
add Virtual Platform Pose (ablation)Voxel RCNN · Pi3DET Vehicle -> DroneAP BEV @0.7: 52.85 -> 59.83Improved
combine RPJ and VPP (ablation)Voxel RCNN · Pi3DET Vehicle -> DroneAP BEV @0.7: 52.85 -> 64.52Improved
add KL probabilistic feature alignment (ablation)Voxel RCNN · Pi3DET Vehicle -> DroneAP 3D @0.7: 41.50 -> 46.83Improved
add Geometry-Aware Transformation Descriptor (ablation)Voxel RCNN · Pi3DET Vehicle -> DroneAP 3D @0.7: 46.83 -> 47.75Improved
add Geometry-Aware Transformation Descriptor (ablation)Voxel RCNN · Pi3DET Vehicle -> QuadrupedAP BEV @0.7: 55.72 -> 55.54No clear effect
add Random Platform Jitter to top vehicle detectorsPart A2 · Pi3DET VehicleAP 3D @0.7: 48.23 -> 47.56Hurt
add RPJ to PV-RCNN++PV-RCNN++ · Pi3DET QuadrupedAP 3D @0.7: 22.35 -> 31.09Improved
adapt from nuScenes to KITTI with Pi3DET-Net without RPJSECOND-IoU · nuScenes -> KITTIaverage AP 3D: 43.43 -> 46.45Improved

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