AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data

Tuo Feng, Wenguan Wang, Ruijie Quan, Yi Yang

ECCV 2024 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 19 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
pre-train MH-P with S2SS and PPC instead of training from scratch (ablation)MH-P · ScanObjectNN PB_T50_RSoverall accuracy (%): 85.9 -> 87.8Improved
pre-train MH-V with S2SS and PPC instead of training from scratch (ablation)MH-V · S3DIS Area5mIoU (%): 70.3 -> 72.7Improved
replace single-shape pre-training with S2SS pseudo scenes (ablation)MH-V · S3DIS Area5mIoU (%): 70.5 -> 72.7Improved
pre-train on single shape data without pseudo scenes (ablation)MH-V · S3DIS Area5mIoU (%): 70.3 -> 70.5No clear effect
scale pseudo-scene pre-training data to UHD and LHD instead of ScanNet real scenes (ablation)MH-V · S3DIS Area5mIoU (%): 73.5 -> 74.1Improved
use four scales instead of two (ablation)MH-P · ScanObjectNN PB_T50_RSoverall accuracy (%): 82.3 -> 87.8Improved
use four scales instead of two (ablation)MH-V · S3DIS Area5mIoU (%): 62.3 -> 72.7Improved
integrate high-resolution features from all scales into final output instead of only the last scale (ablation)MH-V · S3DIS Area5mIoU (%): 71.6 -> 72.7Improved
increase shapes per pseudo scene M beyond the optimum (ablation)S2SS · S3DIS Area5mIoU (%): 72.7 (M=6) vs 72.5 (M=8), 72.6 (M=10)No clear effect
increase M from 1 to 4 shapes per scene (ablation)S2SS · ScanObjectNN PB_T50_RSoverall accuracy (%): 86.8 -> 87.8Improved
use MH-P backbone instead of PointGPT-S transformer, ShapeNet pre-trainingMH-PS · ModelNet40overall accuracy (%): 94.0 -> 94.1No clear effect
pre-train MH-V on pseudo scenes for outdoor detection and segmentation versus ShapeNet-pretrained PointDifMH-VS · SemanticKITTI valmIoU (%): 71.3 -> 70.8Hurt

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