arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.06959cs.CV
收藏

鲁棒特征的图像风格化

Image Stylization for Robust Features

Niantic;Aalto University(阿尔托大学)

Iaroslav Melekhov, Gabriel J. Brostow, Juho Kannala, Daniyar Turmukhambetov

摘要:

对于许多计算机视觉任务来说,对视点和外观变化都具有鲁棒性的局部特征是至关重要的。在这项工作中,我们调查,如果真实感图像风格化提高鲁棒性的本地功能,不仅昼夜,而且天气和季节变化。我们表明,图像风格化除了颜色增强是一个强大的方法学习强大的功能。我们在视觉定位基准上评估了学习的特征,尽管只使用合成单应性进行训练而没有地面实况3D对应,但性能优于最先进的基线模型。我们使用经过训练的特征网络来参加自动驾驶长期视觉定位和基于地图的定位挑战赛,并获得有竞争力的分数。

英文摘要:

Local features that are robust to both viewpoint and appearance changes are crucial for many computer vision tasks. In this work we investigate if photorealistic image stylization improves robustness of local features to not only day-night, but also weather and season variations. We show that image stylization in addition to color augmentation is a powerful method of learning robust features. We evaluate learned features on visual localization benchmarks, outperforming state of the art baseline models despite training without ground-truth 3D correspondences using synthetic homographies only. We use trained feature networks to compete in Long-Term Visual Localization and Map-based Localization for Autonomous Driving challenges achieving competitive scores.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑