OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model

TL;DR

OpenMaskDINO3D leverages large language models to enable natural language-driven 3D segmentation of point cloud data, advancing 3D perception by integrating reasoning and segmentation capabilities.

Contribution

This paper introduces OpenMaskDINO3D, a novel framework that combines LLMs with 3D segmentation, including a SEG token for high-precision natural language-based point cloud segmentation.

Findings

Effective 3D segmentation on ScanNet dataset

High accuracy in natural language-guided point cloud segmentation

Versatile performance across various 3D tasks

Abstract

Although perception systems have made remarkable advancements in recent years, particularly in 2D reasoning segmentation, these systems still rely on explicit human instruction or pre-defined categories to identify target objects before executing visual recognition tasks. Such systems have matured significantly, demonstrating the ability to reason and comprehend implicit user intentions in two-dimensional contexts, producing accurate segmentation masks based on complex and implicit query text. However, a comparable framework and structure for 3D reasoning segmentation remain absent. This paper introduces OpenMaskDINO3D, a LLM designed for comprehensive 3D understanding and segmentation. OpenMaskDINO3D processes point cloud data and text prompts to produce instance segmentation masks, excelling in many 3D tasks. By introducing a SEG token and object identifier, we achieve high-precision 3D segmentation mask generation, enabling the model to directly produce accurate point cloud segmentation results from natural language instructions. Experimental results on large-scale ScanNet datasets validate the effectiveness of our OpenMaskDINO3D across various tasks.