PMPNet: Pixel Movement Prediction Network for Monocular Depth Estimation in Dynamic Scenes

TL;DR

This paper introduces PMPNet, a novel monocular depth estimation method for dynamic scenes that leverages a pixel movement prediction module and deformable support window to improve accuracy, especially around edges.

Contribution

The paper presents a new approach combining pixel movement prediction and deformable support window modules for improved depth estimation in dynamic scenes.

Findings

Outperforms existing methods on KITTI, Make3D, and NYU Depth V2 datasets.

Demonstrates effectiveness of the pixel movement prediction module.

Shows benefits of deformable support window in edge accuracy.

Abstract

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.