PoserNet: Refining Relative Camera Poses Exploiting Object Detections

TL;DR

PoserNet is a novel graph neural network that refines relative camera poses by leveraging objectness regions across multiple views, significantly improving pose accuracy without relying on explicit semantic object detections.

Contribution

This paper introduces PoserNet, the first to use objectness regions for global camera pose refinement, enhancing existing motion averaging algorithms.

Findings

Improves median rotation error by 62 degrees.

Effective across varied graph sizes.

Enhances optimization-based motion averaging.

Abstract

The estimation of the camera poses associated with a set of images commonly relies on feature matches between the images. In contrast, we are the first to address this challenge by using objectness regions to guide the pose estimation problem rather than explicit semantic object detections. We propose Pose Refiner Network (PoserNet) a light-weight Graph Neural Network to refine the approximate pair-wise relative camera poses. PoserNet exploits associations between the objectness regions - concisely expressed as bounding boxes - across multiple views to globally refine sparsely connected view graphs. We evaluate on the 7-Scenes dataset across varied sizes of graphs and show how this process can be beneficial to optimisation-based Motion Averaging algorithms improving the median error on the rotation by 62 degrees with respect to the initial estimates obtained based on bounding boxes. Code and data are available at https://github.com/IIT-PAVIS/PoserNet.