NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training
This work addresses the need for efficient depth estimation in virtual and augmented reality applications, though it appears incremental as it builds on existing self-supervised methods.
The paper tackles self-supervised monocular depth estimation by introducing NimbleD, a framework that uses pseudo-labels from a large vision model and large-scale video pre-training without camera intrinsics, resulting in lightweight models achieving performance comparable to state-of-the-art models.
We introduce NimbleD, an efficient self-supervised monocular depth estimation learning framework that incorporates supervision from pseudo-labels generated by a large vision model. This framework does not require camera intrinsics, enabling large-scale pre-training on publicly available videos. Our straightforward yet effective learning strategy significantly enhances the performance of fast and lightweight models without introducing any overhead, allowing them to achieve performance comparable to state-of-the-art self-supervised monocular depth estimation models. This advancement is particularly beneficial for virtual and augmented reality applications requiring low latency inference. The source code, model weights, and acknowledgments are available at https://github.com/xapaxca/nimbled .