通过预测像素运动轨迹提升动态场景单目深度估计精度
PMPNet: Pixel Movement Prediction Network for Monocular Depth Estimation in Dynamic Scenes
- 假设像素在短距离内沿直线移动，构建二维三角约束损失
- 在KITTI和NYU Depth V2上达到优于现有方法的深度估计精度
- 适合处理边缘模糊问题，尤其适用于复杂动态场景
本文提出一种用于动态场景下单目深度估计的新方法。我们首先从理论上分析了动态场景中物体运动轨迹的任意性。为克服这一问题，假设像素在短距离内沿直线运动，并将其总结为二维欧氏空间中的三角约束损失。为解决边缘区域的深度不一致问题，提出可变形支持窗口模块，能够从不同形状物体中学习特征，提升边缘处深度估计准确性。所提模型在两个室外数据集KITTI和Make3D以及一个室内数据集NYU Depth V2上进行训练与测试。定量与定性结果表明，相比其他方法，本模型表现更优。在KITTI数据集上的消融实验进一步验证了像素运动预测模块和可变形支持窗口模块的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。