SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.01413 · 2024

MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large 2D vision-language models (2D-LLMs) have gained significant attention by bridging Large Language Models (LLMs) with images using a simple projector. Inspired by their success, large 3D point cloud-language models (3D-LLMs) also integrate point clouds into LLMs. However, directly aligning point clouds with LLM requires expensive training costs, typically in hundreds of GPU-hours on A100, which hinders the development of 3D-LLMs. In this paper, we introduce MiniGPT-3D, an efficient and powerful 3D-LLM that achieves multiple SOTA results while training for only 27 hours on one RTX 3090. Specifically, we propose to align 3D point clouds with LLMs using 2D priors from 2D-LLMs, which can leverage the similarity between 2D and 3D visual information. We introduce a novel four-stage training strategy for modality alignment in a cascaded way, and a mixture of query experts module to adaptively aggregate features with high efficiency. Moreover, we utilize parameter-efficient fine-tuning methods LoRA and Norm fine-tuning, resulting in only 47.8M learnable parameters, which is up to 260x fewer than existing methods. Extensive experiments show that MiniGPT-3D achieves SOTA on 3D object classification and captioning tasks, with significantly cheaper training costs. Notably, MiniGPT-3D gains an 8.12 increase on GPT-4 evaluation score for the challenging object captioning task compared to ShapeLLM-13B, while the latter costs 160 total GPU-hours on 8 A800. We are the first to explore the efficient 3D-LLM, offering new insights to the community. Code and weights are available at https://github.com/TangYuan96/MiniGPT-3D.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.01413")
get_code_for_paper("2405.01413")
have("2405.01413")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2405.01413.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2405.01413.svg)](https://syntology.ai/paper/2405.01413)

Connect an agent — have() is free.