AI Paper Atlas

Research map / Point clouds / Segmentation and detection

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

Hao Yang, Haiyang Wang, Di Dai, Liwei Wang

NeurIPS 2023 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 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
add PRED pre-training to DSVT-P CenterPointCenterPoint detector · nuScenes valmAP: 61.5 -> 64.2Improved
add PRED pre-training to SecondSecond · nuScenes valmAP: 52.2 -> 55.2Improved
add PRED pre-training to DSVTDSVT · nuScenes testmAP: 68.4 -> 70.1Improved
add PRED pre-training to CenterPoint on ONCECenterPoint · ONCE valmAP: 64.28 -> 67.41Improved
increase pre-training data from small to large (ablation)PRED CenterPoint · ONCE valmAP: 65.87 -> 66.72 -> 67.41Improved
add PRED pre-training to DSVT for BEV map segmentationDSVT · nuScenes BEV mapmIoU: 51.6 -> 55.0Improved
swap backbone to 2D Conv (ablation)PRED · nuScenes valmAP: 50.0 -> 53.0Improved
replace direct projection with neural rendering w/ depth (ablation)PRED · nuScenes valmAP: 62.0 -> 64.2Improved
add depth supervision to rendering (ablation)PRED · nuScenes valmAP: 63.5 -> 64.2Improved
add depth filtering to projection (ablation)PRED projection · nuScenes valmAP: 62.0 -> 62.8Improved
add confidence weight and class balance sampling to semantic loss (ablation)PRED · nuScenes valmAP: 62.5 -> 64.2Improved
use lidar view instead of image view for depth supervision (ablation)PRED · nuScenes valmAP: 63.6 -> 64.2Improved

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