PMPNet: Pixel Movement Prediction Network for Monocular Depth Estimation in Dynamic Scenes
This work addresses depth estimation in dynamic scenes for computer vision applications, presenting an incremental improvement with novel modules.
The paper tackles monocular depth estimation in dynamic scenes by addressing arbitrary object movement and depth inconsistency around edges, achieving success on KITTI, Make3D, and NYU Depth V2 datasets with quantitative and qualitative improvements over other approaches.
In this paper, we propose a novel method for monocular depth estimation in dynamic scenes. We first explore the arbitrariness of object's movement trajectory in dynamic scenes theoretically. To overcome the arbitrariness, we use assume that points move along a straight line over short distances and then summarize it as a triangular constraint loss in two dimensional Euclidean space. To overcome the depth inconsistency problem around the edges, we propose a deformable support window module that learns features from different shapes of objects, making depth value more accurate around edge area. The proposed model is trained and tested on two outdoor datasets - KITTI and Make3D, as well as an indoor dataset - NYU Depth V2. The quantitative and qualitative results reported on these datasets demonstrate the success of our proposed model when compared against other approaches. Ablation study results on the KITTI dataset also validate the effectiveness of the proposed pixel movement prediction module as well as the deformable support window module.