This repository contains trained weights for object detection and ellipse prediction for visual localization. These weights were trained on the Chess scene of the 7-Scenes dataset and can be loaded in the neural networks available at https://gitlab.inria.fr/tangram/3d-aware-ellipses-for-visual-localization and https://gitlab.inria.fr/tangram/level-set-based-camera-pose-estimation. They provide object detections in images and predicted ellipses which are then used to estimate the camera pose.

3D-Aware-Ellipses-for-Visual-Localization, 1.0

Level-Set-Based-Camera-Pose-Estimation, 1.0