Brief

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, enabling the app to create outfit recommendations and virtual try-ons. This integration has significantly reduced operational costs for Alta Daily, allowing them to process millions of images affordably and focus on enhancing user experience. AI

Researchers have introduced COCOTree, a new dataset and benchmark designed for the task of open tree-structured visual decomposition. This task involves segmenting images into hierarchical trees of visual components with flexible granularity. The dataset was generated using a novel pipeline that combines Large Vision-Language Models with SAM 3 for semantic reasoning and geometric grounding, resulting in over 2.1K images and 1.8M structural nodes with an open vocabulary of 3.5K labels. A new evaluation metric, Open Tree Quality (OTQ), has also been proposed to assess mask precision, label accuracy, and structural consistency. AI

Researchers have developed a new system for monitoring construction site safety using video analysis. The pipeline processes footage from various cameras through a three-stage architecture, starting with object detection for personal protective equipment and hazards, followed by segmentation refinement, and finally, a sophisticated VLM verification process. This advanced verification stage uses a persona-scaffolded adversarial chain-of-thought protocol to improve precision and control hallucinations, mapping violations to OSHA standards and generating worker safety reports. AI