论文标题
CBWLOSS：双向加权损失有限
CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose
论文作者
论文摘要
光度差异被广泛用作训练神经网络的监督信号，以估算未标记的单眼视频的深度和相机姿势。但是，这种方法对模型优化有害，因为场景中的阻塞和移动对象违反了基本的静态场景假设。此外，无纹理区域中的像素或更少的歧视性像素阻碍了模型培训。为了解决这些问题，在本文中，我们分别利用仿射转换和视图合成产生的流场和深度结构的差异来处理移动的对象和遮挡。其次，我们通过在不添加网络的情况下通过更语义和上下文信息来衡量功能之间的差异来减轻纹理区域对模型优化的影响。另外，尽管双向分量在每个亚目标函数中都使用，但仅将一对图像推理了一次，这有助于减少开销。广泛的实验和视觉分析证明了所提出的方法的有效性，在相同条件下，在没有引入其他辅助信息的情况下，该方法的表现优于现有的最先进的自我监管方法。
Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions and moving objects in a scene violate the underlying static scenario assumption. In addition, pixels in textureless regions or less discriminative pixels hinder model training. To solve these problems, in this paper, we deal with moving objects and occlusions utilizing the difference of the flow fields and depth structure generated by affine transformation and view synthesis, respectively. Secondly, we mitigate the effect of textureless regions on model optimization by measuring differences between features with more semantic and contextual information without adding networks. In addition, although the bidirectionality component is used in each sub-objective function, a pair of images are reasoned about only once, which helps reduce overhead. Extensive experiments and visual analysis demonstrate the effectiveness of the proposed method, which outperform existing state-of-the-art self-supervised methods under the same conditions and without introducing additional auxiliary information.
