AI Paper Atlas

Research map / 3D vision / 3D generation

MergeOcc: Bridge the Domain Gap between Different LiDARs for Robust Occupancy Prediction

Zikun Xu, Shaobing Xu

ICCV 2025 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 1 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
align point cloud range to minimum range (ablation)MergeOcc · OpenOccupancy-nuScenesgeometric IoU: 25.4 -> 38.2Improved
align point cloud range to minimum range (ablation)MergeOcc · SemanticKITTIgeometric IoU: 36.7 -> 70.0Improved
align range to maximum range instead of none (ablation)MergeOcc · OpenOccupancy-nuScenesgeometric IoU: 25.4 -> 16.5Hurt
add geometric statistic alignment alone (dataset-specific norm) (ablation)MergeOcc · OpenOccupancy-nuScenesgeometric IoU: 25.4 -> 14.7Hurt
add geometric statistic alignment on top of range alignment (ablation)MergeOcc · OpenOccupancy-nuScenesgeometric IoU: 38.2 -> 38.4No clear effect
add semantic label mapping (ablation)MergeOcc · OpenOccupancy-nuScenessemantic mIoU: 21.4 -> 22.9Improved
add semantic label mapping (ablation)MergeOcc · SemanticKITTIgeometric IoU: 69.9 -> 70.1No clear effect
use geometric alignment only in the backbone instead of all norm layers (ablation)MergeOcc · OpenOccupancy-nuScenesgeometric IoU: 37.0 -> 38.4Improved
range alignment under single-dataset training (ablation)MergeOcc · OpenOccupancy-nuScenesgeometric IoU: 30.9 -> 27.4Hurt
pre-train on SK then fine-tune on OO-nu (ablation)L-CONet · OpenOccupancy-nuScenesgeometric IoU: 30.1 -> 26.3Hurt
pre-train on OO-nu then fine-tune on SK (ablation)L-CONet · SemanticKITTIgeometric IoU: 55.6 -> 53.3Hurt
train on both datasets with MergeOcc instead of single datasetL-CONet · SemanticKITTIgeometric IoU: 55.6 -> 70.1Improved

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