Camera Pose Auto-Encoders for Improving Pose Regression

TL;DR

This paper introduces Camera Pose Auto-Encoders trained via a Teacher-Student approach to enhance camera pose estimation accuracy and enable low-memory image reconstruction, achieving state-of-the-art results on standard benchmarks.

Contribution

It presents a novel auto-encoder framework for camera poses that improves pose regression accuracy and supports image reconstruction from pose encodings.

Findings

Achieves new state-of-the-art position accuracy on CambridgeLandmarks and 7Scenes.

Enables low-memory image reconstruction from pose encodings.

Improves pose estimation through a light-weight test-time optimization.

Abstract

Absolute pose regressor (APR) networks are trained to estimate the pose of the camera given a captured image. They compute latent image representations from which the camera position and orientation are regressed. APRs provide a different tradeoff between localization accuracy, runtime, and memory, compared to structure-based localization schemes that provide state-of-the-art accuracy. In this work, we introduce Camera Pose Auto-Encoders (PAEs), multilayer perceptrons that are trained via a Teacher-Student approach to encode camera poses using APRs as their teachers. We show that the resulting latent pose representations can closely reproduce APR performance and demonstrate their effectiveness for related tasks. Specifically, we propose a light-weight test-time optimization in which the closest train poses are encoded and used to refine camera position estimation. This procedure achieves a new state-of-the-art position accuracy for APRs, on both the CambridgeLandmarks and 7Scenes benchmarks. We also show that train images can be reconstructed from the learned pose encoding, paving the way for integrating visual information from the train set at a low memory cost. Our code and pre-trained models are available at https://github.com/yolish/camera-pose-auto-encoders.