RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on ...
DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features ...
Abstract: Object-based visual-inertial odometry (VIO) is applied broadly in location service for ground vehicles and robotics, but tends to be limited to research of ...
Abstract: The Segment Anything Model 2 (SAM 2) has demonstrated exceptional performance in object segmentation tasks but encounters challenges in visual object tracking, particularly in handling ...