Imagen de Portada

Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3)

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Niehorster, Diederick C., Nyström, Marcus
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)
por: Maquiling, Virmarie, et al.
Publicado: (2023)

LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images
por: Byrne, Sean Anthony, et al.
Publicado: (2023)

Precise localization of corneal reflections in eye images using deep learning trained on synthetic data
por: Byrne, Sean Anthony, et al.
Publicado: (2023)

ClickSAM: Fine-tuning Segment Anything Model using click prompts for ultrasound image segmentation
por: Guo, Aimee, et al.
Publicado: (2024)

Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images
por: Maquiling, Virmarie, et al.
Publicado: (2024)

SAM 3: Segment Anything with Concepts
por: Carion, Nicolas, et al.
Publicado: (2025)

Compress Any Segment Anything Model (SAM)
por: Fan, Juntong, et al.
Publicado: (2025)

MedSAM3: Delving into Segment Anything with Medical Concepts
por: Liu, Anglin, et al.
Publicado: (2025)

SGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation
por: Tang, Zixuan, et al.
Publicado: (2026)

X-SAM: From Segment Anything to Any Segmentation
por: Wang, Hao, et al.
Publicado: (2025)

The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation
por: Sapkota, Ranjan, et al.
Publicado: (2025)

SparseSAM: Structured Sparsification of Activations in Segment Anything Models
por: Tran, Hoai-Chau, et al.
Publicado: (2026)

SAM 3D: 3Dfy Anything in Images
por: SAM 3D Team, et al.
Publicado: (2025)

Q-SAM2: Accurate Quantization for Segment Anything Model 2
por: Farronato, Nicola, et al.
Publicado: (2025)

RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation
por: Li, Yonglin, et al.
Publicado: (2023)

CamSAM2: Segment Anything Accurately in Camouflaged Videos
por: Zhou, Yuli, et al.
Publicado: (2025)

Is SAM3 ready for pathology segmentation?
por: Kong, Qiuyu, et al.
Publicado: (2026)

Region-Guided Attack on the Segment Anything Model (SAM)
por: Liu, Xiaoliang, et al.
Publicado: (2024)

MedVL-SAM2: A unified 3D medical vision-language model for multimodal reasoning and prompt-driven segmentation
por: Xing, Yang, et al.
Publicado: (2026)

SAM 2: Segment Anything in Images and Videos
por: Ravi, Nikhila, et al.
Publicado: (2024)

DeiSAM: Segment Anything with Deictic Prompting
por: Shindo, Hikaru, et al.
Publicado: (2024)

Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO
por: Mumuni, Fuseini, et al.
Publicado: (2024)

AMA-SAM: Adversarial Multi-Domain Alignment of Segment Anything Model for High-Fidelity Histology Nuclei Segmentation
por: Qian, Jiahe, et al.
Publicado: (2025)

WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
por: Zhu, Lianghui, et al.
Publicado: (2024)

MedSAM2: Segment Anything in 3D Medical Images and Videos
por: Ma, Jun, et al.
Publicado: (2025)

Med-PerSAM: One-Shot Visual Prompt Tuning for Personalized Segment Anything Model in Medical Domain
por: Yoon, Hangyul, et al.
Publicado: (2024)

EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss
por: Zhang, Zhuoyang, et al.
Publicado: (2024)

MGD-SAM2: Multi-view Guided Detail-enhanced Segment Anything Model 2 for High-Resolution Class-agnostic Segmentation
por: Shen, Haoran, et al.
Publicado: (2025)

RobustSAM: Segment Anything Robustly on Degraded Images
por: Chen, Wei-Ting, et al.
Publicado: (2024)

Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation
por: Avogaro, Niccolo, et al.
Publicado: (2025)

Assessing Foundational Medical 'Segment Anything' (Med-SAM1, Med-SAM2) Deep Learning Models for Left Atrial Segmentation in 3D LGE MRI
por: Mehrnia, Mehri, et al.
Publicado: (2024)

Point-SAM: Promptable 3D Segmentation Model for Point Clouds
por: Zhou, Yuchen, et al.
Publicado: (2024)

TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
por: Ding, Zhaoyuan, et al.
Publicado: (2026)

AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation
por: Li, Chengyin, et al.
Publicado: (2023)

GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation
por: Deng, Ken, et al.
Publicado: (2025)

BiSeg-SAM: Weakly-Supervised Post-Processing Framework for Boosting Binary Segmentation in Segment Anything Models
por: Su, Encheng, et al.
Publicado: (2025)

SPDA-SAM: A Self-prompted Depth-Aware Segment Anything Model for Instance Segmentation
por: Shang, Yihan, et al.
Publicado: (2026)

EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3
por: Zeng, Chengxi, et al.
Publicado: (2025)

Gaussian Grouping: Segment and Edit Anything in 3D Scenes
por: Ye, Mingqiao, et al.
Publicado: (2023)

DepthSeg: Depth prompting in remote sensing semantic segmentation
por: Zhou, Ning, et al.
Publicado: (2025)