تقرير
Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometry
العنوان: | Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometry |
---|---|
المؤلفون: | Chidlovskii, Boris, Antsfeld, Leonid |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | For the task of simultaneous monocular depth and visual odometry estimation, we propose learning self-supervised transformer-based models in two steps. Our first step consists in a generic pretraining to learn 3D geometry, using cross-view completion objective (CroCo), followed by self-supervised finetuning on non-annotated videos. We show that our self-supervised models can reach state-of-the-art performance 'without bells and whistles' using standard components such as visual transformers, dense prediction transformers and adapters. We demonstrate the effectiveness of our proposed method by running evaluations on six benchmark datasets, both static and dynamic, indoor and outdoor, with synthetic and real images. For all datasets, our method outperforms state-of-the-art methods, in particular for depth prediction task. Comment: 8 pages, to appear in ICRA'24 |
نوع الوثيقة: | Working Paper |
الوصول الحر: | http://arxiv.org/abs/2406.11019Test |
رقم الانضمام: | edsarx.2406.11019 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |