AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Salient Object Detection for Point Clouds

Songlin Fan, Wei Gao, Ge Li

ECCV 2022 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 54 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 SPB to PointNet++ encoder (ablation)PointNet++ · PCSOD testIoU: 0.608 -> 0.624Improved
add PPB 1 (global semantics) on top of SPB (ablation)PointNet++ +SPB · PCSOD testIoU: 0.624 -> 0.639Improved
add PPB 2 (multi-scale) on top of SPB and PPB 1 (ablation)PointNet++ +SPB +PPB 1 · PCSOD testIoU: 0.639 -> 0.656Improved
add PPB 2 on top of SPB and PPB 1 (ablation)PointNet++ +SPB +PPB 1 · PCSOD testMAE: 0.073 -> 0.069Improved
use mean-max reduction instead of mean reduction (ablation)PPB · PCSOD testF-measure: 0.764 -> 0.769Improved
use mean-max reduction instead of max reduction (ablation)PPB · PCSOD testF-measure: 0.765 -> 0.769Improved
use mean-max reduction instead of attentive reduction (ablation)PPB · PCSOD testMAE: 0.074 -> 0.069Improved
use mean-max reduction instead of attentive reduction (ablation)PPB · PCSOD testIoU: 0.658 -> 0.656Hurt
replace PointNet++ with proposed model with PPB and SPBPointNet++ · PCSOD testF-measure: 0.738 -> 0.769Improved
compare RandLA to PointNet++ for SODRandLA · PCSOD testMAE: 0.077 -> 0.127Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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