AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Learning Latent Part-Whole Hierarchies for Point Clouds

Xiang Gao, Wei Hu, Renjie Liao

IJCV 2025 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 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 control variate to REINFORCE estimator (ablation)MC-REINFORCE · Chair middle levelaccuracy: 72.39 ± 0.95 -> 73.75 ± 0.19Improved
add control variate to REINFORCE estimator (ablation)MC-REINFORCE · Lamp middle levelaccuracy: 75.65 ± 1.86 -> 76.23 ± 0.52Improved
add control variate to REINFORCE estimator (ablation)MC-REINFORCE · Table middle levelaccuracy: 70.40 ± 0.58 -> 71.64 ± 0.27Improved
add control variate to REINFORCE estimator (ablation)MC-REINFORCE · Lamp top levelaccuracy: 76.78 ± 0.82 -> 77.49 ± 0.59Improved
use latent part-whole model instead of PointNetMC-REINFORCE · multi-level segmentation, middle levelmean accuracy: 59.53 -> 66.69Improved
use latent part-whole model instead of PointNetMC-REINFORCE · multi-level segmentation, top levelmean accuracy: 85.19 -> 87.39Improved
use MC-REINFORCE inference instead of Pathwiselatent part-whole model · middle levelmean accuracy: 64.93 -> 66.69Improved
increase number of Monte Carlo samples (5 to 100) (ablation)MC inference · middle level segmentationaccuracy and stdImproved
decrease temperature tau of pathwise estimator from large values (ablation)MC-Pathwise · Chair, Lamp, Table middle levelaccuracyMixed

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