AI Paper Atlas

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

RECO: Region-Aware Compensation for Extrinsic Perturbations in Roadside 3D Detection

Junsheng Du, Yuhuan Lu, Zhaocheng He

ECCV 2026 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 0 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 region-aware compensation (soft) instead of none, yaw mu=0 (ablation)RECO · DAIR-V2X-I persistent yawCar AP easy: 67.5595 -> 70.4639Improved
add region-aware compensation (soft) instead of none, z mu=0 (ablation)RECO · DAIR-V2X-I persistent zCar AP easy: 48.3313 -> 72.616Improved
replace global compensation with soft range-aware compensation, yaw mu=0 (ablation)RECO · DAIR-V2X-I persistent yawCar AP easy: 33.2416 -> 70.4639Improved
use soft sigmoid gate instead of hard assignment, yaw mu=-2 (ablation)RECO · DAIR-V2X-I persistent yawCar AP easy: 40.0773 -> 49.3382Improved
use soft gate instead of hard assignment, z mu=0 (ablation)RECO · DAIR-V2X-I persistent zCar AP easy: 68.3201 -> 72.616Improved
use soft gate instead of hard assignment, z mu=-2 (ablation)RECO · DAIR-V2X-I persistent zCar AP easy: 31.6210 -> 31.0973Mixed
add global compensation to uncompensated model, yaw mu=0 (ablation)detector · DAIR-V2X-I persistent yawCar AP easy: 67.5595 -> 33.2416Hurt
add global compensation to uncompensated model, yaw mu=-2 (ablation)detector · DAIR-V2X-I persistent yawCar AP easy: 18.0282 -> 32.2572Improved
compare RECO with BEVHeight++ under z transient perturbationRECO · DAIR-V2X-I (z)Car AP easy: 55.8025 -> 72.6160Improved
compare RECO with BEVHeight++ under Rope3D yawRECO · Rope3D (yaw)Car AP easy: 50.3703 -> 65.3942Improved
compare RECO with BEVHeight under pitch perturbationRECO · DAIR-V2X-I (pitch)Car AP easy: 53.1881 -> 65.3235Improved
compare RECO with BEVHeight on pedestrian under pitchRECO · DAIR-V2X-I (pitch)Pedestrian AP easy: 9.3655 -> 8.4951Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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