AI Paper Atlas

Research map / Point clouds / Segmentation and detection

GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure

Bin Yang, Mohamed Abdelsamad, Miao Zhang, Michael Ulrich, Yakov Miron, Abhinav Valada, Alexandru Paul Condurache

ECCV 2026 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 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 hallucinated ghost-point targets to the predictorPointINS · nuScenes (decoder probing)mAP: 56.7 -> 59.5Improved
add hallucinated ghost-point targets to the predictorPointINS · nuScenes (decoder probing)NDS: 62.5 -> 64.2Improved
add hallucination pretraining then fine-tunePTv3 · nuScenes (full fine-tuning)mAP: 63.8 -> 67.5Improved
restrict predictor to masked observed points (no hallucination) (ablation)PointINS · nuScenes (decoder probing)mAP: 56.7 -> 57.3Improved
replace ghost targets with zero offsets and uniform Softmaps (ablation)PointINS · nuScenes (decoder probing)mAP: 57.3 -> 57.6No clear effect
add informative hallucinated targets rather than zero targets (ablation)GhostPoint · nuScenes (decoder probing)mAP: 57.6 -> 59.5Improved
swap masked points for the same number of hallucinated points (ablation)GhostPoint · nuScenes (decoder probing)mAP: 59.4 -> 59.5No clear effect
add neighborhood sampling with KNN interpolation, then predictor with warmup (ablation)GhostPoint · nuScenes (decoder probing)mAPImproved
add an auxiliary box regression target (ablation)GhostPoint · nuScenes (decoder probing)mAPHurt
add KNN-based token initialization for teacher ghost tokens (ablation)GhostPoint · nuScenes (decoder probing)mAPImproved
increase predictor depth beyond 3 blocks (ablation)GhostPoint · nuScenes (decoder probing)mAPNo clear effect
add GhostPoint pretraining under 0.1% labelsPTv3 · Waymo (0.1% labels)mAP: 20.0 -> 28.5Improved

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