FocalPose++: Focal Length and Object Pose Estimation Via Render and Compare.

We introduce FocalPose++, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object. The contributions of this work are threefold. First, we derive a focal length update rule that extends an existing state-of-the-art render-and-compare 6D pose estimator to address the joint estimation task.

Basic level scene understanding: categories, attributes and structures.

A longstanding goal of computer vision is to build a system that can automatically understand a 3D scene from a single image. This requires extracting semantic concepts and 3D information from 2D images which can depict an enormous variety of environments that comprise our visual world. This paper summarizes our recent efforts toward these goals.

Implementation of the first wellness-fitness evaluation for the Dallas Fire-Rescue Department.

More than 100 firefighters lose their lives in the line of duty each year; many of these deaths are caused by cardiovascular events and underlying coronary heart disease. In addition, firefighters are at higher-than-normal risk of developing certain types of cancer. To improve health and fitness among its firefighters, the Dallas Fire-Rescue Department developed and implemented an annual wellness-fitness program in 2008.