ePose: Let's Make EfficientPose More Generally Applicable
This work addresses incremental improvements for 3D object detection in computer vision, focusing on specific datasets like Linemod.
The paper tackles improving EfficientPose, a 3D object detection model, by adding object size inference and simplifying data collection and loss calculations, with evaluation on the Linemod dataset and a new 'Occlusion 1-class' subset.
EfficientPose is an impressive 3D object detection model. It has been demonstrated to be quick, scalable, and accurate, especially when considering that it uses only RGB inputs. In this paper we try to improve on EfficientPose by giving it the ability to infer an object's size, and by simplifying both the data collection and loss calculations. We evaluated ePose using the Linemod dataset and a new subset of it called "Occlusion 1-class". We also outline our current progress and thoughts about using ePose with the NuScenes and the 2017 KITTI 3D Object Detection datasets. The source code is available at https://github.com/tbd-clip/EfficientPose.