Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3)
2026/03/18 by Diederick C. Niehorster, Marcus Nyström · 1 voice
Computer Science · #cs.AI #cs.CV
paper · pdf · doi:10.48550/arxiv.2603.17715
Abstract
Previous work has reported that vision foundation models show promising zero-shot performance in eye image segmentation. Here we examine whether the latest iteration of the Segment Anything Model, SAM3, offers better eye image segmentation performance than SAM2, and explore the performance of its new concept (text) prompting mode. Eye image segmentation performance was evaluated using diverse datasets encompassing both high-resolution high-quality videos from a lab environment and the TEyeD dataset consisting of challenging eye videos acquired in the wild. Results show that in most cases SAM3 with either visual or concept prompts did not perform better than SAM2, for both lab and in-the-wild datasets. Since SAM2 not only performed better but was also faster, we conclude that SAM2 remains the best option for eye image segmentation. We provide our adaptation of SAM3's codebase that allows processing videos of arbitrary duration.
Citations
- Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data
- SAM 3: Segment Anything with Concepts
- Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images
- Towards Unsupervised Eye-Region Segmentation for Eye Tracking
- Window Attention is Bugged: How not to Interpolate Position Embeddings
- Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
- Micrograph segmentations for DDEVD
- Segment Anything
- Pistol: Pupil Invisible Supportive Tool to extract Pupil, Iris, Eye Opening, Eye Movements, Pupil and Iris Gaze Vector, and 2D as well as 3D Gaze
- Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark
- TEyeD: Over 20 million real-world eye images with Pupil, Eyelid, and Iris 2D and 3D Segmentations, 2D and 3D Landmarks, 3D Eyeball, Gaze Vector, and Eye Movement Types
- Gaze-in-wild: A dataset for studying eye and head coordination in everyday activities
- PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
- PupilNet: Convolutional Neural Networks for Robust Pupil Detection
- In the Eye of the Beholder: A Survey of Models for Eyes and Gaze
Discussions
Related