| 2025.11 |
SAM 3: Segment Anything with Concepts |
Code |
arXiv'2025 |
| 2025.11 |
SAM 3D: 3Dfy Anything in Images |
Code |
arXiv'2025 |
| 2025.11 |
SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation |
Code |
arXiv'2025 |
| 2025.11 |
Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data |
- |
arXiv'2025 |
| 2025.12 |
SAM3-UNet: Simplified Adaptation of Segment Anything Model 3 |
Code |
arXiv'2025 |
| 2025.12 |
SAM3-I: Segment Anything with Instructions |
Code |
arXiv'2025 |
| 2025.12 |
The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation |
- |
arXiv'2025 |
| 2025.12 |
More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery |
- |
arXiv'2025 |
| 2025.12 |
SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images |
Code |
arXiv'2025 |
| 2025.12 |
Depth-Copy-Paste: Multimodal and Depth-Aware Compositing for Robust Face Detection |
- |
arXiv'2025 |
| 2025.12 |
Generalization vs. Specialization: Evaluating Segment Anything Model (SAM3) Zero-Shot Segmentation Against Fine-Tuned YOLO Detectors |
Code |
arXiv'2025 |
| 2025.12 |
On the Effectiveness of Textual Prompting with Lightweight Fine-Tuning for SAM3 Remote Sensing Segmentation |
- |
arXiv'2025 |
| 2025.12 |
Memory-Enhanced SAM3 for Occlusion-Robust Surgical Instrument Segmentation |
Code |
arXiv'2025 |
| 2025.12 |
SAM Audio: Segment Anything in Audio |
Code |
arXiv'2025 |
| 2025.12 |
Rethinking Memory Design in SAM-Based Visual Object Tracking |
Code |
arXiv'2025 |
| 2025.12 |
Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting |
Code |
arXiv'2025 |
| 2026.01 |
SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM3 |
Code |
arXiv'2026 |
| 2026.01 |
Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation |
Code |
arXiv'2026 |
| 2026.01 |
OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3 |
Code |
arXiv'2026 |
| 2026.01 |
C-RADIOv4 (Tech Report) |
Code |
arXiv'2026 |
| 2026.02 |
Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation |
Code |
arXiv'2026 |
| 2026.02 |
VLM-Guided Iterative Refinement for Surgical Image Segmentation with Foundation Models |
- |
arXiv'2026 |
| 2026.02 |
SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation |
Code |
arXiv'2026 |
| 2026.02 |
SAM 3D Body: Robust Full-Body Human Mesh Recovery |
Code |
arXiv'2026 |
| 2026.02 |
CAD-Prompted SAM3: Geometry-Conditioned Instance Segmentation for Industrial Objects |
- |
arXiv'2026 |
| 2026.03 |
OPTED: Open Preprocessed Trachoma Eye Dataset Using Zero-Shot SAM 3 Segmentation |
- |
arXiv'2026 |
| 2026.03 |
Detect Anything in Real Time: From Single-Prompt Segmentation to Multi-Class Detection |
Code |
arXiv'2026 |
| 2026.03 |
Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3) |
- |
arXiv'2026 |
| 2026.03 |
Synergistic Perception and Generative Recomposition: A Multi-Agent Orchestration for Expert-Level Building Inspection |
- |
arXiv'2026 |
| 2026.03 |
Adapting Segment Anything Model 3 for Concept-Driven Lesion Segmentation in Medical Images: An Experimental Study |
Code |
arXiv'2026 |