FoodSAM: Any Food Segmentation

TL;DR

FoodSAM is a comprehensive zero-shot segmentation framework for food images that integrates semantic, instance, panoptic, and promptable segmentation, demonstrating high performance and pioneering multi-level segmentation capabilities in food image analysis.

Contribution

FoodSAM introduces the first unified framework for instance, panoptic, and promptable segmentation of food images, enhancing SAM's zero-shot capabilities with novel integration techniques.

Findings

Effective zero-shot segmentation of food images achieved

First to combine instance, panoptic, and promptable segmentation in food domain

Demonstrates high performance and versatility across segmentation tasks

Abstract

In this paper, we explore the zero-shot capability of the Segment Anything Model (SAM) for food image segmentation. To address the lack of class-specific information in SAM-generated masks, we propose a novel framework, called FoodSAM. This innovative approach integrates the coarse semantic mask with SAM-generated masks to enhance semantic segmentation quality. Besides, we recognize that the ingredients in food can be supposed as independent individuals, which motivated us to perform instance segmentation on food images. Furthermore, FoodSAM extends its zero-shot capability to encompass panoptic segmentation by incorporating an object detector, which renders FoodSAM to effectively capture non-food object information. Drawing inspiration from the recent success of promptable segmentation, we also extend FoodSAM to promptable segmentation, supporting various prompt variants. Consequently, FoodSAM emerges as an all-encompassing solution capable of segmenting food items at multiple levels of granularity. Remarkably, this pioneering framework stands as the first-ever work to achieve instance, panoptic, and promptable segmentation on food images. Extensive experiments demonstrate the feasibility and impressing performance of FoodSAM, validating SAM's potential as a prominent and influential tool within the domain of food image segmentation. We release our code at https://github.com/jamesjg/FoodSAM.