PREGAN: Pose Randomization and Estimation for Weakly Paired Image Style Translation

TL;DR

PREGAN introduces a weakly-paired style translation method that uses pose randomization and estimation to enable style transfer across images with pose errors, enhancing robustness for robot applications.

Contribution

The paper proposes a novel weakly-paired setting and a style translation framework that incorporates pose randomization and estimation, improving style transfer without requiring precise data pairing.

Findings

Effective style translation demonstrated on simulated and real data.

Improved performance in downstream tasks like classification and segmentation.

Robustness to pose errors in style transfer tasks.

Abstract

Utilizing the trained model under different conditions without data annotation is attractive for robot applications. Towards this goal, one class of methods is to translate the image style from another environment to the one on which models are trained. In this paper, we propose a weakly-paired setting for the style translation, where the content in the two images is aligned with errors in poses. These images could be acquired by different sensors in different conditions that share an overlapping region, e.g. with LiDAR or stereo cameras, from sunny days or foggy nights. We consider this setting to be more practical with: (i) easier labeling than the paired data; (ii) better interpretability and detail retrieval than the unpaired data. To translate across such images, we propose PREGAN to train a style translator by intentionally transforming the two images with a random pose, and to estimate the given random pose by differentiable non-trainable pose estimator given that the more aligned in style, the better the estimated result is. Such adversarial training enforces the network to learn the style translation, avoiding being entangled with other variations. Finally, PREGAN is validated on both simulated and real-world collected data to show the effectiveness. Results on down-stream tasks, classification, road segmentation, object detection, and feature matching show its potential for real applications. https://github.com/wrld/PRoGAN