AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointLLM: Empowering Large Language Models to Understand Point Clouds

Runsen Xu, Xiaolong Wang, Tai Wang, Yilun Chen, Jiangmiao Pang, Dahua Lin

ECCV 2024 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 240 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
use 3 projection layers instead of none (ablation)PointLLM-7B · Generative 3D classification avgaccuracy: 50.63 -> 52.82Improved
use 4 projection layers instead of 3 (ablation)PointLLM-13B · Generative 3D classification avgaccuracy: 53.39 -> 51.40Hurt
add max pooling of point tokens before projection (ablation)PointLLM-7B · Generative 3D classification avgaccuracy: 52.82 -> 48.72Hurt
add max pooling of point tokens before projection (ablation)PointLLM-7B · training costA100 GPU-hours: 126 -> 34Improved
add multi-round conversation data to fine-tuning (ablation)PointLLM-7B · Generative 3D classification avgaccuracy: 40.14 -> 45.79Improved
add detailed description data to fine-tuning (ablation)PointLLM-7B · Generative 3D classification avgaccuracy: 45.79 -> 52.82Improved
increase alignment data volumePointLLM-7B · Generative 3D classificationaccuracyImproved
use point cloud input instead of single-view imagesPointLLM · Generative 3D classification avgaccuracy: 44.86 -> 52.82 (LLaVA-7B vs PointLLM-7B)Improved
use 13B backbone instead of 7BPointLLM · Objaverse 3D captioninghallucination: 0.66 -> 0.84Hurt
prompt for captions of at most 20 words (ablation)PointLLM-13B · Objaverse 3D captioningBLEU-1: 3.83 -> 17.09 BLEU-1; correctness 3.10 -> 2.12Mixed

Later papers that compared with this method

7 later accepted papers report PointLLM-7B as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

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