AI Paper Atlas

Research map / Point clouds / Point cloud classification

SPOT: Scalable 3D Pre-Training via Occupancy Prediction for Learning Transferable 3D Representations

Xiangchao Yan, Runjian Chen, Bo Zhang, Hancheng Ye, Renqiu Xia, Jiakang Yuan, Hongbin Zhou, Xinyu Cai, Botian Shi, Wenqi Shao, Ping Luo, Yu Qiao and 2 more

TPAMI 2025 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 16 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 occupancy prediction pre-training (ablation)SECOND · nuScenes (5% fine-tune)mAP: 32.16 -> 36.55Improved
add loss balancing (ablation)occupancy pre-training · nuScenesmAP: 36.55 -> 37.90Improved
add beam re-sampling (ablation)occupancy pre-training · nuScenesmAP: 37.90 -> 38.63Improved
add dataset balancing (ablation)occupancy pre-training · nuScenesmAP: 38.63 -> 40.39Improved
add occupancy prediction (ablation)SECOND · ONCEmAP: 35.96 -> 36.00No clear effect
add beam re-sampling (ablation)occupancy pre-training · ONCEmAP: 37.30 -> 39.19Improved
use occupancy pre-training instead of detection pre-training (ablation)CenterPoint · nuScenes detmAP: 40.89 -> 47.47Improved
use occupancy pre-training instead of segmentation pre-training (ablation)CenterPoint · nuScenes detmAP: 36.23 -> 47.47Improved
use detection pre-training instead of no pre-training (ablation)CenterPoint · nuScenes detmAP: 42.37 -> 40.89Hurt
increase pre-training data from 5% to 100% (ablation)SPOT SECOND · nuScenes (5% fine-tune)mAP: 37.96 -> 42.57Improved
pre-train with weak labels only (no human labels)SPOT SECOND · nuScenes (5% fine-tune)mAP: 32.16 -> 42.24Improved
train from scratch for 150 epochs instead of 30 (ablation)SECOND · nuScenes detmAP: 32.16 -> 36.79Improved

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