Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency
This work addresses the challenge of accurate depth and motion estimation for autonomous systems operating in complex, dynamic environments, offering an incremental improvement over existing methods.
This paper tackles the problem of monocular depth estimation in dynamic scenes by explicitly modeling the 6-DoF motion of multiple dynamic objects and ego-motion. The framework achieves state-of-the-art performance on both depth and motion estimation tasks on the KITTI and Cityscapes datasets.
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we highlight the fundamental difference between inverse and forward projection while modeling the individual motion of each rigid object, and propose a geometrically correct projection pipeline using a neural forward projection module. Second, we design a unified instance-aware photometric and geometric consistency loss that holistically imposes self-supervisory signals for every background and object region. Lastly, we introduce a general-purpose auto-annotation scheme using any off-the-shelf instance segmentation and optical flow models to produce video instance segmentation maps that will be utilized as input to our training pipeline. These proposed elements are validated in a detailed ablation study. Through extensive experiments conducted on the KITTI and Cityscapes dataset, our framework is shown to outperform the state-of-the-art depth and motion estimation methods. Our code, dataset, and models are available at https://github.com/SeokjuLee/Insta-DM .