AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointTPA: Dynamic Network Parameter Adaptation for 3D Scene Understanding

Siyuan Liu, Chaoqun Zheng, Xin Zhou, Tianrui Feng, Dingkang Liang, Xiang Bai

CVPR 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 0 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 DPP (dynamic parameter projector) to static adapters (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 76.8 -> 77.8Improved
add SNG grouping on top of DPP (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 77.8 -> 78.4Improved
number of bases [4,4,2,2,2] instead of [8,8,4,4,4] (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 78.0 -> 78.4Improved
number of bases [4,4,2,2,2] instead of [1,1,1,1,1] (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 77.7 -> 78.4Improved
use 200 groups instead of 400 in the first stage (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 78.0 -> 78.4Improved
use grouping instead of no grouping (1*) (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 77.8 -> 78.4Improved
scaling factor s=1.0 instead of 0.1 (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 78.1 -> 78.4Improved
DPLayer on down-projection only instead of both (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 77.8 -> 78.4Improved
add DPLayer (dynamic weights) to DPP (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 77.5 -> 78.4Improved
use last block of each stage instead of dense DPP (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 77.8 -> 78.4Improved
mixed insertion at last block of each stage instead of last block only (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 77.6 -> 78.4Improved
use space-filling-curve serialization instead of none (ablation)PointTPA · ScanNet Val (no decoder)mIoU: 77.8 -> 78.4Improved

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