AI Paper Atlas

Research map / Point clouds / Point cloud classification

Direction-aware 3D Large Multimodal Models

Quan Liu, Weihao Xuan, Junjue Wang, Naoto Yokoya, Ling Shao, Shijian Lu

CVPR 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 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 PoseAlign-T (ego-aligned point cloud)3D-LLAVA · ScanRefer valmIoU: 42.6 -> 55.4Improved
add PoseAlign-T3D-LLAVA · Multi3DRefer valmIoU: 48.1 -> 54.3Improved
add PoseAlign-T3D-LLAVA · Scan2Cap valLLM-as-judge accuracy: 28.1 -> 31.4Improved
add PoseAlign-T3D-LLAVA · Scan2Cap valCIDEr@0.5: 77.4 -> 76.1Hurt
add PoseAlign-EChat-Scene · ScanQA valLLM-as-judge accuracy: 43.9 -> 44.7Improved
add PoseAlign-TLL3DA · ScanQA valLLM-as-judge accuracy: 34.7 -> 35.6Improved
use PoseRecover poses rather than random poses (ablation)3D-LLAVA + PoseAlign · ScanRefer valmIoU: 39.0 -> 55.4Improved
use transform rather than embedding the pose (PoseAlign-E) (ablation)3D-LLAVA · ScanRefer valmIoU: 43.2 -> 68.5Improved
use transform rather than pose text prompt (PoseAlign-P) (ablation)3D-LLAVA · ScanRefer valmIoU: 44.2 -> 68.5Improved
add Clip ratio X=0.3 instead of Top pose selection (ablation)3D-LLAVA + PoseAlign-T · Scan2Cap valLLM-as-judge accuracy: 29.7 -> 31.4Mixed
vary Clip ratio X from 0.0 to 0.49 (ablation)3D-LLAVA + PoseAlign-T · ScanQA valLLM-as-judge accuracy: 47.3 -> 46.9No clear effect
clip ratio X=0.4 or higher (Chat-Scene PoseAlign-E) (ablation)Chat-Scene · Scan2Cap valLLM-as-judge accuracy: 26.9 -> 6.2Hurt

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