Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometry
This addresses the problem of 3D scene understanding from monocular images for robotics and autonomous systems, representing a strong incremental improvement over existing methods.
The paper tackles simultaneous monocular depth and visual odometry estimation by proposing a two-step self-supervised approach using transformer-based models with cross-view completion pretraining and finetuning on videos, achieving state-of-the-art performance across six diverse benchmark datasets, particularly for depth prediction.
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.