AI Paper Atlas

Research map / Point clouds / Point cloud classification

Points Meet Pixels: Bridging 2D Vision-Language Model and 3D Perception Gaps for Point Cloud Quality Assessment

Mingxuan Li, Zihao Huang, Xiaohui Chu, Fazhan Zhang, Bohan Fu, Runze Hu

AAAI 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
PMP-PCQA vs second-best methodLMM-PCQA · SJTU-PCQASRCC: 0.925 -> 0.957Improved
PMP-PCQA vs second-best methodLMM-PCQA · LS-PCQASRCC: 0.731 -> 0.763Improved
PMP-PCQA vs second-best methodCLIP-PCQA · BASICSSRCC: 0.856 -> 0.892Improved
add FCA module (ablation)PMP-PCQA · SJTU-PCQASRCC: 0.923 -> 0.957Improved
add SAE module (ablation)PMP-PCQA · SJTU-PCQASRCC: 0.943 -> 0.957Improved
add TAM module (ablation)PMP-PCQA · SJTU-PCQASRCC: 0.946 -> 0.957Improved
add FCA module (ablation)PMP-PCQA · LS-PCQASRCC: 0.722 -> 0.763Improved
use entropy-adaptive threshold instead of fixed 0.6 (ablation)TAM · SJTU-PCQASRCC: 0.947 -> 0.957Improved
use 64 sampling points instead of 256 (ablation)SAE · SJTU-PCQASRCC: 0.941 -> 0.957Improved
use 64 sampling points instead of 16 (ablation)SAE · SJTU-PCQASRCC: 0.945 -> 0.957Improved
add text branch (ablation)image+point model · SJTU-PCQASRCC: 0.925 -> 0.957Improved
add image branch to point+text (ablation)point+text model · SJTU-PCQASRCC: 0.839 -> 0.957Improved

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