Segment Anything Model
PulseAugur coverage of Segment Anything Model — every cluster mentioning Segment Anything Model across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
Human-AI collaboration boosts medical image segmentation accuracy
Researchers have developed Hi-Seg, a framework that enhances the Segment Anything Model (SAM) for pulmonary nodule segmentation in medical imaging. This human-in-the-loop system allows annotators, including non-medical …
-
New SPDA-SAM Model Enhances Instance Segmentation with Depth Awareness
Researchers have introduced SPDA-SAM, a novel self-prompted and depth-aware model for instance segmentation that builds upon the Segment Anything Model (SAM). This new model incorporates a Semantic-Spatial Self-prompt M…
-
AI advances medical image segmentation with new frameworks and techniques · 8 sources tracked
Researchers are developing advanced AI frameworks for medical image segmentation, focusing on improving accuracy and efficiency. Hi-Seg enhances the Segment Anything Model (SAM) for pulmonary nodule segmentation through…
-
New framework adapts Segment Anything Model for seismic interpretation
Researchers have developed a new framework for adapting the Segment Anything Model (SAM) for seismic interpretation without requiring extensive retraining. This approach utilizes seismic attributes and visualization cho…
-
New adapter module enhances AI segmentation models under varied lighting
Researchers have developed a new adapter module called Lighting Convolutional-Attention (LCA) to improve the robustness of foundation models like SAM for instance segmentation under varied lighting conditions. LCA proce…
-
New method integrates elliptical shape prior to improve SAM segmentation
Researchers have developed a new method to enhance the Segment Anything Model (SAM) by incorporating an elliptical shape prior. This approach uses a parameterized elliptical contour field to guide the segmentation proce…
-
New method matches 2D polygons for pose estimation
Researchers have introduced a novel Zero-shot Polygon Matching paradigm with Pre-trained Models (Z(PM)2) to address the challenges of matching 2D polygons in stereo imagery. This method leverages pre-trained models like…
-
SAMatcher uses Segment Anything for robust image feature matching
Researchers have developed SAMatcher, a new framework for robust feature matching in images. This method leverages the Segment Anything Model (SAM) to predict co-visible region masks and bounding boxes, which serve as s…
-
SAM adapted for microscopy with synthetic data
Researchers have adapted the Segment Anything Model (SAM) for segmenting mitochondria in fluorescence microscopy images. The primary challenge addressed is the domain shift between natural images and microscopy data, al…
-
New AI method segments cell types with single click
Researchers have developed a new framework called Chain-of-Prompts (CoP) that significantly improves cell instance segmentation in histopathology images. This training-free method requires only a single click per cell t…
-
SAM pipeline generates pixel-level annotations for autonomous driving data
Researchers have developed a new method to create dense, pixel-level annotations for autonomous driving datasets that previously only had bounding boxes. This pipeline utilizes the Segment Anything Model (SAM) to conver…
-
AI Pipeline Generates Animations from Text Prompts
Researchers have developed a system called Generative Animations that uses a pipeline of AI models to create animations from natural language prompts. This system chains Large Language Models (LLMs) for understanding th…
-
PinPoint method improves image segmentation without training
Researchers have developed PinPoint, a novel method for referring image segmentation that improves accuracy without requiring additional training. PinPoint addresses prompt ambiguity by selecting informative interior po…
-
New DeCoDrift framework stabilizes foundation segmentation models
Researchers have identified a new failure mode in foundation segmentation models, termed "decoder coupling drift," which occurs when these models are used iteratively. This drift causes errors to accumulate as the model…
-
Alta Daily fashion app digitizes wardrobes using Meta's SAM
Alta Daily, a fashion app launched in 2025, leverages Meta's Segment Anything Model (SAM) to digitize users' wardrobes. The app allows users to upload photos of their clothing, which SAM then segments with high accuracy…
-
New FAST-ME algorithm uses AI for efficient video motion analysis
Researchers have developed FAST-ME, a novel algorithm for efficient motion estimation in video analysis, particularly for resource-constrained IoT devices. This method integrates Optimal Stopping Theory with Foundation …
-
SAM enhances autonomous driving datasets with pixel-level annotations
Researchers have developed a new pipeline using the Segment Anything Model (SAM) to generate dense, pixel-level annotations for autonomous driving datasets that previously only had bounding boxes. This SAM-based approac…
-
Logic-guided fine-tuning boosts weakly supervised segmentation models
Researchers have developed a novel approach to weakly supervised semantic segmentation by integrating differentiable fuzzy logic with deep learning models. This method allows for the unification of weak annotations and …
-
AI model approaches human parity in organoid image segmentation
Researchers have developed a new composite method for segmenting organoid images, combining the Segment Anything Model (SAM) with a domain-specific tool. This approach aims to accurately measure the size and shape of de…
-
SAMamba3D adapts Segment Anything for generalizable 3D pore-scale image segmentation
Researchers have developed SAMamba3D, a new framework designed to improve the generalizability of 3D image segmentation for multiphase pore-scale rock images. This method adapts the existing Segment Anything Model (SAM)…