AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature Space

Wentao Wang, Haoran Xu, Guang Tan

ICLR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Collaborative multi-agent perception · 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
remove feature projector (ablation)GT-Space · OPV2V Agent 1mAP@70: 0.683 -> 0.814Improved
remove feature projector (ablation)GT-Space · V2XSet Agent 1mAP@70: 0.604 -> 0.806Improved
add combinatorial contrastive loss (ablation)GT-Space · OPV2V Agent 1mAP@70: 0.721 -> 0.814Improved
add combinatorial contrastive loss (ablation)GT-Space · V2XSet Agent 1mAP@70: 0.709 -> 0.806Improved
use ground-truth feature space instead of PointPillar feature space (ablation)GT-Space · OPV2V Agent 1mAP@70: 0.795 -> 0.814Improved
use ground-truth feature space instead of PointPillar feature space (ablation)GT-Space · V2XSet Agent 1mAP@50: 0.830 -> 0.873Improved
use GT-Space instead of STAMP for LiDAR ego with camera collaboratorcollaborative perception · OPV2V A1+A3AP@70: 0.734 -> 0.766Improved
use GT-Space instead of HEAL for LiDAR ego with LiDAR collaboratorcollaborative perception · OPV2V A1+A2AP@70: 0.801 -> 0.810Improved
use GT-Space instead of STAMP on V2XSet camera paircollaborative perception · V2XSet A1+A3AP@70: 0.703 -> 0.741Improved
add communication latency up to 500 msGT-Space · OPV2Vdetection accuracyNo clear effect
add Gaussian pose noiseGT-Space · OPV2Vdetection accuracyNo clear effect

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