PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model
This addresses the limitation in 3D perception systems for users needing more intuitive, reasoning-based interactions, though it is incremental as it builds on existing segmentation methods with new query handling.
The paper tackles the problem of 3D part segmentation by enabling systems to handle implicit textual queries through reasoning, rather than relying on explicit human instructions, and achieves competitive performance compared to models using explicit queries while adding capabilities like part identification and reasoning.
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.