Sam3
PulseAugur coverage of Sam3 — every cluster mentioning Sam3 across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
PicoSAM3 model enables real-time segmentation on image sensors
Researchers have developed PicoSAM3, a new lightweight segmentation model designed for real-time execution on edge devices and even directly on image sensors. This model, with 1.3 million parameters, utilizes a dense CN…
-
New AI model uses CAD to segment industrial objects
Researchers have developed a new instance segmentation method called CAD-Prompted SAM3, which utilizes Computer-Aided Design (CAD) models to guide the segmentation process. This approach overcomes the limitations of tex…
-
New methods advance open-vocabulary semantic segmentation
Researchers have developed new methods for open-vocabulary semantic segmentation, a task that allows models to identify and segment novel concepts based on text descriptions. One approach, the Semantic Calibration Netwo…
-
AI pipeline automates labeling of unknown objects in images
Researchers have developed an automated pipeline to label objects in images that are not recognized by existing open-vocabulary models. This system aims to reduce the tedious manual work of creating bounding boxes for t…
-
Visionary Future develops object-centric latent world models
A Shenzhen-based AI team, Visionary Future, is developing an
-
New zero-shot tracking system excels in multi-animal studies
Researchers have developed a new zero-shot multi-animal tracking system that leverages vision foundation models, specifically adapting SAM2MOT with Grounding DINO and the Segment Anything Model 2. This method achieves s…
-
New methods boost remote sensing visual grounding accuracy
Researchers have developed new methods to improve visual grounding in remote sensing imagery, a task that involves locating specific image regions described by text. Their approach combines a specialized remote sensing …
-
FungiTastic framework tackles low-data mushroom segmentation
Researchers have introduced FungiTastic, a novel training-free framework for fine-grained semantic segmentation of mushrooms, particularly in low-data scenarios. The two-stage approach first uses SAM3 for class-agnostic…
-
New XAI Framework Enhances Bacteria Detection Explanations
Researchers have developed SAM-Sode, a new eXplainable AI (XAI) framework designed to improve the interpretability of tiny bacteria detection in medical diagnostics. Traditional methods struggle with the fine details an…
-
OpenVTON-Bench: New benchmark for high-resolution virtual try-on evaluation
Researchers have introduced OpenVTON-Bench, a large-scale benchmark designed to improve the evaluation of virtual try-on systems. This benchmark includes approximately 100,000 high-resolution image pairs and utilizes ad…
-
VL-SAM-v3 enhances open-world object detection with visual memory
Researchers have introduced VL-SAM-v3, a novel framework designed to enhance open-world object detection by incorporating external visual memory. This approach augments existing methods, which often struggle with fine-g…
-
New methods improve open-vocabulary object detection robustness and adaptation
Researchers have introduced several new methods to improve open-vocabulary object detection, a field that aims to identify arbitrary objects based on human prompts. One approach, EBOD, integrates a prompt-based detector…
-
ViewSAM model uses foundation models for weakly supervised cross-view object tracking
Researchers have developed ViewSAM, a novel framework for weakly supervised Cross-view Referring Multi-Object Tracking (CRMOT). This approach leverages foundation models like SAM2 and SAM3 to generate pseudo-supervision…
-
From Scene to Object: Text-Guided Dual-Gaze Prediction
Researchers have developed a novel dual-branch gaze prediction framework to improve interpretable driver attention prediction for autonomous driving. This framework addresses limitations in existing datasets by construc…
-
INSIGHT pipeline transfers 2D image understanding to 3D for indoor public safety
Researchers have developed a new pipeline called INSIGHT to improve indoor scene intelligence for public safety applications. This system transfers understanding from 2D images into 3D metric space, addressing the scarc…
-
AgentRVOS pipeline refines video object segmentation with explicit agent roles
Researchers have developed AgentRVOS, a novel pipeline for referring video object segmentation (Ref-VOS) that leverages a semantic hypothesis generator called Sa2VA. This system employs an agent-based architecture to re…