Saved in:
Bibliographic Details
Main Authors: AlMughrabi, Ahmad, Rivo, Guillermo, Jiménez-Farfán, Carlos, Haroon, Umair, Al-Areqi, Farid, Jung, Hyunjun, Busam, Benjamin, Marques, Ricardo, Radeva, Petia
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.07581
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917209030262784
author AlMughrabi, Ahmad
Rivo, Guillermo
Jiménez-Farfán, Carlos
Haroon, Umair
Al-Areqi, Farid
Jung, Hyunjun
Busam, Benjamin
Marques, Ricardo
Radeva, Petia
author_facet AlMughrabi, Ahmad
Rivo, Guillermo
Jiménez-Farfán, Carlos
Haroon, Umair
Al-Areqi, Farid
Jung, Hyunjun
Busam, Benjamin
Marques, Ricardo
Radeva, Petia
contents Food image segmentation is a critical task for dietary analysis, enabling accurate estimation of food volume and nutrients. However, current methods suffer from limited multi-view data and poor generalization to new viewpoints. We introduce BenchSeg, a novel multi-view food video segmentation dataset and benchmark. BenchSeg aggregates 55 dish scenes (from Nutrition5k, Vegetables & Fruits, MetaFood3D, and FoodKit) with 25,284 meticulously annotated frames, capturing each dish under free 360° camera motion. We evaluate a diverse set of 20 state-of-the-art segmentation models (e.g., SAM-based, transformer, CNN, and large multimodal) on the existing FoodSeg103 dataset and evaluate them (alone and combined with video-memory modules) on BenchSeg. Quantitative and qualitative results demonstrate that while standard image segmenters degrade sharply under novel viewpoints, memory-augmented methods maintain temporal consistency across frames. Our best model based on a combination of SeTR-MLA+XMem2 outperforms prior work (e.g., improving over FoodMem by ~2.63% mAP), offering new insights into food segmentation and tracking for dietary analysis. In addition to frame-wise spatial accuracy, we introduce a dedicated temporal evaluation protocol that explicitly quantifies segmentation stability over time through continuity, flicker rate, and IoU drift metrics. This allows us to reveal failure modes that remain invisible under standard per-frame evaluations. We release BenchSeg to foster future research. The project page including the dataset annotations and the food segmentation models can be found at https://amughrabi.github.io/benchseg.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07581
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BenchSeg: A Large-Scale Dataset and Benchmark for Multi-View Food Video Segmentation
AlMughrabi, Ahmad
Rivo, Guillermo
Jiménez-Farfán, Carlos
Haroon, Umair
Al-Areqi, Farid
Jung, Hyunjun
Busam, Benjamin
Marques, Ricardo
Radeva, Petia
Computer Vision and Pattern Recognition
Food image segmentation is a critical task for dietary analysis, enabling accurate estimation of food volume and nutrients. However, current methods suffer from limited multi-view data and poor generalization to new viewpoints. We introduce BenchSeg, a novel multi-view food video segmentation dataset and benchmark. BenchSeg aggregates 55 dish scenes (from Nutrition5k, Vegetables & Fruits, MetaFood3D, and FoodKit) with 25,284 meticulously annotated frames, capturing each dish under free 360° camera motion. We evaluate a diverse set of 20 state-of-the-art segmentation models (e.g., SAM-based, transformer, CNN, and large multimodal) on the existing FoodSeg103 dataset and evaluate them (alone and combined with video-memory modules) on BenchSeg. Quantitative and qualitative results demonstrate that while standard image segmenters degrade sharply under novel viewpoints, memory-augmented methods maintain temporal consistency across frames. Our best model based on a combination of SeTR-MLA+XMem2 outperforms prior work (e.g., improving over FoodMem by ~2.63% mAP), offering new insights into food segmentation and tracking for dietary analysis. In addition to frame-wise spatial accuracy, we introduce a dedicated temporal evaluation protocol that explicitly quantifies segmentation stability over time through continuity, flicker rate, and IoU drift metrics. This allows us to reveal failure modes that remain invisible under standard per-frame evaluations. We release BenchSeg to foster future research. The project page including the dataset annotations and the food segmentation models can be found at https://amughrabi.github.io/benchseg.
title BenchSeg: A Large-Scale Dataset and Benchmark for Multi-View Food Video Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.07581