PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model

TL;DR

This paper introduces PARIS3D, a novel reasoning-based 3D part segmentation task that interprets implicit textual queries to segment 3D objects and generate explanations, supported by a large curated dataset and a capable model.

Contribution

It presents a new reasoning-based segmentation task, a large dataset, and a model that understands implicit queries and reasons about 3D object parts.

Findings

Achieves competitive segmentation performance with implicit queries.

Can generate natural language explanations for segmentation.

Demonstrates reasoning and world knowledge integration.

Abstract

Recent advancements in 3D perception systems have significantly improved their ability to perform visual recognition tasks such as segmentation. However, these systems still heavily rely on explicit human instruction to identify target objects or categories, lacking the capability to actively reason and comprehend implicit user intentions. We introduce a novel segmentation task known as reasoning part segmentation for 3D objects, aiming to output a segmentation mask based on complex and implicit textual queries about specific parts of a 3D object. To facilitate evaluation and benchmarking, we present a large 3D dataset comprising over 60k instructions paired with corresponding ground-truth part segmentation annotations specifically curated for reasoning-based 3D part segmentation. We propose a model that is capable of segmenting parts of 3D objects based on implicit textual queries and generating natural language explanations corresponding to 3D object segmentation requests. Experiments show that our method achieves competitive performance to models that use explicit queries, with the additional abilities to identify part concepts, reason about them, and complement them with world knowledge. Our source code, dataset, and trained models are available at https://github.com/AmrinKareem/PARIS3D.