PointLLM: Empowering Large Language Models to Understand Point Clouds

By Runsen Xu, Xiaolong Wang, Tai Wang, Yilun Chen, Jiangmiao Pang, Dahua Lin. European Conference on Computer Vision, 2023

396 citations recorded by the source corpus.

The unprecedented advancements in Large Language Models (LLMs) have shown a profound impact on natural language processing but are yet to fully embrace the realm of 3D understanding. This paper introduces PointLLM, a preliminary effort to fill this gap, enabling LLMs to understand point clouds and offering a new avenue beyond 2D visual data. PointLLM understands colored object point clouds with human instructions and generates contextually appropriate responses, illustrating its grasp of point clouds and common sense. Specifically, it leverages a point cloud encoder with a powerful LLM to effectively fuse geometric, appearance, and linguistic information. We collect a novel dataset comprising 660K simple and 70K complex point-text instruction pairs to enable a two-stage training strategy: aligning latent spaces and subsequently instruction-tuning the unified model. To rigorously evaluate the perceptual and generalization capabilities of PointLLM, we establish two benchmarks: Generative 3D Object Classification and 3D Object Captioning, assessed through three different methods, including human evaluation, GPT-4/ChatGPT evaluation, and traditional metrics. Experimental results reveal PointLLM's superior performance over existing 2D and 3D baselines, with a notable achievement in human-evaluated object captioning tasks where it surpasses human annotators in over 50% of the samples. Codes, datasets, and benchmarks are available at https://github.com/OpenRobotLab/PointLLM .

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6bcc6ab9c28805d4067e99b2cdc7524550fe80e1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Peng Gao
3. Hongsheng Li
4. Xiaogang Wang
5. Bo Li
6. Luc Van Gool
7. Song-Chun Zhu
8. Yu Qiao

Citations in the corpus

• A survey on multimodal large language models (2023, neutral): “In order to further inspect what roles LLMs exactly play in LLM-Aided Visual Reasoning systems, existing related works are divided into three types: • LLM as a Controller • LLM as a Decision Maker”
• VLMEvalKit: An Open-Source ToolKit for Evaluating Large Multi-Modality Models (2024, background): “Most of the research has focused on LMMs for image and text [5,29], but research has also been extended to other modalities, such as audiotext [10], video [7, 25, 40], or point clouds [46, 47].”
• LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models (2024, background): “Traditionally, researchers have approached these challenges by training separate task-specific models for each application scenario, e.g., multi-image [1, 19, 27], video [7, 29, 66], and 3D [14, 15, 58].”
• MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? (2024, background): “They extend LLMs to tackle a diverse range of tasks and domains, including the mainstream 2D images [35, 15, 1, 31] and other modalities, such as 3D point clouds [23, 60, 27], audio [24, 52], and video [65, 6].”
• A Survey on Knowledge Distillation of Large Language Models (2024, background): “This approach is especially relevant for leveraging the feed-back from teacher to train student models (Bai et al., 2022a; Cui et al., 2023a; Luo et al., 2023c; Agarwal et al., 2024; Chen et al., 2024a; Ma et al., 2023a; Pang et al., 2023; Du et al., 2023a).”
• EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain (2024, background): “D point clouds [31], [32], [33] are being integrated and aligned.”
• An Embodied Generalist Agent in 3D World (2023, positive): “Specifically, we utilize the Point-BERT checkpoint from PointLLM (Xu et al., 2023), which has adapted Point-BERT to 6-channel (XYZRGB) input and learned a language-aligned representation for 3D objects.”
• Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning (2026, unknown): “PointLLM [39] employs a pretrained 3D encoder, and LL3DA [6] further introduces a Q-former [18] to extract more semantically rich features.”