IEEE

Bridging the Gap Between Semantics and Geometry in SLAM: A Semantic-Geometric Tight-Coupling Monocular Visual Object SLAM System

Abstract: Existing object-level simultaneous localization and mapping (SLAM) methods often overlook the correspondence between semantic information and geometric features, resulting in a significant ...
Frontiers

Associations of hemoglobin trajectories and time in target hemoglobin range with adverse pregnancy outcomes: a real-world pregnancy records-based study

1 Shanghai First Maternity and Infant Hospital Affiliated to Tongji University School of Medicine, Shanghai, China 2 Department of Obstetrics and Gynecology, Shanghai Ninth People’s Hospital ...
IEEE

Visual-Tactile Inference of 2.5D Object Shape From Marker Texture

Abstract: Visual-tactile sensing affords abundant capabilities for contact-rich object manipulation tasks including grasping and placing. Here we introduce a shape-from-texture inspired contact shape ...
about.fb

New Segment Anything Models Make it Easier to Detect Objects and Create 3D Reconstructions

We’re introducing SAM 3 and SAM 3D, the newest additions to our Segment Anything Collection, which advance AI understanding of the visual world. SAM 3 enables detection and tracking of objects in ...
GitHub

UniPixel: Unified Object Referring and Segmentation

UniPixel is a unified MLLM for pixel-level vision-language understanding. It flexibly supports a variety of fine-grained tasks, including image/video segmentation, regional understanding, and a novel ...