Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose FlexDepth, a new approach to estimating depth from single camera images without needing labeled data. Their method separates training for static backgrounds and moving objects, allowing better depth estimates in complex driving scenes. They introduce a scale-driven decoder that efficiently combines features at different sizes to improve accuracy. Experiments show their model runs fast on mobile devices and works well across various scales without extra input data.
monocular depth estimationself-supervised learningdynamic objectsscale-driven decoderfeature fusionzero-shot generalizationreal-time perceptionautomotive edge devicesGFLOPsbenchmark
Authors
Zhaowen Zhu, Li Zhang, Yujie Chen, Tian Zhang, Yingjie Wang, Mingxia Zhan
Abstract
Self-Supervised Monocular Depth Estimation (MDE) has garnered attention in recent years due to its independence from ground truth. However, most existing models are limited to a single scale and exhibit considerable performance degradation in complex driving environments. Networks specifically designed to handle dynamic traffic participants tend to be overly complex, hindering their deployment on resource-constrained automotive edge devices. To address these limitations and move towards robust driving perception, we propose FlexDepth, a scale-driven and flexible family of self-supervised MDE models tailored for challenging road scenarios. FlexDepth employs a two-stage static-dynamic decoupled training strategy, enabling the independent assessment of confidence for both static backgrounds and dynamic road objects. Furthermore, it introduces a meticulously designed Scale-Driven Decoder (SDD) to dynamically select components based on scale size, facilitating efficient feature fusion and the output of high-precision depth maps. Extensive experiments on standard driving benchmarks demonstrate that without any auxiliary information, our model achieves state-of-the-art performance across arbitrary scales with minimal computational overhead. Our smallest model, Flex-Nano, requires only 0.7 GFLOPs and achieves 37.6 FPS on mobile platforms, ensuring reliable real-time perception while maintaining excellent zero-shot generalization.Our source code is avalible: https://github.com/startnew/flexdepth