Language-Image Models with 3D Understanding
- URL: http://arxiv.org/abs/2405.03685v1
- Date: Mon, 6 May 2024 17:57:27 GMT
- Title: Language-Image Models with 3D Understanding
- Authors: Jang Hyun Cho, Boris Ivanovic, Yulong Cao, Edward Schmerling, Yue Wang, Xinshuo Weng, Boyi Li, Yurong You, Philipp Krähenbühl, Yan Wang, Marco Pavone,
- Abstract summary: We develop a large-scale pre-training dataset for 2D and 3D called LV3D.
Next, we introduce a new MLLM named Cube-LLM and pre-train it on LV3D.
We show that pure data scaling makes a strong 3D perception capability without 3D specific architectural design or training objective.
- Score: 59.499585515469974
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Multi-modal large language models (MLLMs) have shown incredible capabilities in a variety of 2D vision and language tasks. We extend MLLMs' perceptual capabilities to ground and reason about images in 3-dimensional space. To that end, we first develop a large-scale pre-training dataset for 2D and 3D called LV3D by combining multiple existing 2D and 3D recognition datasets under a common task formulation: as multi-turn question-answering. Next, we introduce a new MLLM named Cube-LLM and pre-train it on LV3D. We show that pure data scaling makes a strong 3D perception capability without 3D specific architectural design or training objective. Cube-LLM exhibits intriguing properties similar to LLMs: (1) Cube-LLM can apply chain-of-thought prompting to improve 3D understanding from 2D context information. (2) Cube-LLM can follow complex and diverse instructions and adapt to versatile input and output formats. (3) Cube-LLM can be visually prompted such as 2D box or a set of candidate 3D boxes from specialists. Our experiments on outdoor benchmarks demonstrate that Cube-LLM significantly outperforms existing baselines by 21.3 points of AP-BEV on the Talk2Car dataset for 3D grounded reasoning and 17.7 points on the DriveLM dataset for complex reasoning about driving scenarios, respectively. Cube-LLM also shows competitive results in general MLLM benchmarks such as refCOCO for 2D grounding with (87.0) average score, as well as visual question answering benchmarks such as VQAv2, GQA, SQA, POPE, etc. for complex reasoning. Our project is available at https://janghyuncho.github.io/Cube-LLM.
Related papers
- 3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding [49.15555885075644]
We develop pipeline based on open-source 2D MLLMs and LLMs to generate high-quality 3D-text pairs.
We introduce the 3UR-LLM model, an end-to-end 3D MLLM designed for precise interpretation of 3D scenes.
arXiv Detail & Related papers (2025-01-14T03:50:23Z) - EmbodiedSAM: Online Segment Any 3D Thing in Real Time [61.2321497708998]
Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration.
An online, real-time, fine-grained and highly-generalized 3D perception model is desperately needed.
arXiv Detail & Related papers (2024-08-21T17:57:06Z) - LLMI3D: MLLM-based 3D Perception from a Single 2D Image [77.13869413871028]
multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks.
In this paper, we propose solutions for weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations.
We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM.
arXiv Detail & Related papers (2024-08-14T10:00:16Z) - 3D-LLM: Injecting the 3D World into Large Language Models [60.43823088804661]
Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning.
We propose to inject the 3D world into large language models and introduce a new family of 3D-LLMs.
Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks.
arXiv Detail & Related papers (2023-07-24T17:59:02Z) - ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding [96.95120198412395]
We introduce tri-modal pre-training framework that automatically generates holistic language descriptions for 3D shapes.
It only needs 3D data as input, eliminating the need for any manual 3D annotations, and is therefore scalable to large datasets.
We conduct experiments on two large-scale 3D datasets, NN and ShapeNet, and augment them with tri-modal datasets of 3D point clouds, captioning, and language for training.
Experiments show that NN-2 demonstrates substantial benefits in three downstream tasks: zero-shot 3D classification, standard 3D classification with finetuning, and 3D (3D
arXiv Detail & Related papers (2023-05-14T23:14:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.