Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training

About

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 .

Albert Luginov, Muhammad Shahzad• 2024

Related benchmarks

TaskDatasetResultRank
Monocular Depth EstimationKITTI (Eigen split)
Abs Rel0.092
193
Showing 1 of 1 rows

Other info

Code

Follow for update