Learning to Segment Liquids in Real-world Images

2026-01-02

arXiv.org

AI Summary

This work addresses the challenge of semantic segmentation for transparent and reflective liquids, whose highly variable appearances in real-world scenes hinder safe robotic interaction. To this end, we present LQDS, the first large-scale dataset comprising 5,000 real images spanning 14 liquid categories, and introduce LQDM, a novel liquid segmentation model. LQDM leverages a cross-attention mechanism between a main segmentation branch and a dedicated boundary branch to effectively integrate boundary-aware features, significantly improving segmentation accuracy for complex liquid shapes. Experimental results demonstrate that LQDM outperforms current state-of-the-art methods on the LQDS test set, establishing a strong baseline for the task of liquid semantic segmentation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Security and Privacy: Data transparency and provenance

Abstract

Different types of liquids such as water, wine and medicine appear in all aspects of daily life. However, limited attention has been given to the task, hindering the ability of robots to avoid or interact with liquids safely. The segmentation of liquids is difficult because liquids come in diverse appearances and shapes; moreover, they can be both transparent or reflective, taking on arbitrary objects and scenes from the background or surroundings. To take on this challenge, we construct a large-scale dataset of liquids named LQDS consisting of 5000 real-world images annotated into 14 distinct classes, and design a novel liquid detection model named LQDM, which leverages cross-attention between a dedicated boundary branch and the main segmentation branch to enhance segmentation predictions. Extensive experiments demonstrate the effectiveness of LQDM on the test set of LQDS, outperforming state-of-the-art methods and establishing a strong baseline for the semantic segmentation of liquids.

Problem

• liquid segmentation
• semantic segmentation
• transparent objects
• real-world images
• reflective surfaces

Innovation

• liquid segmentation
• cross-attention mechanism
• boundary-aware segmentation
• LQDS dataset
• transparent object segmentation