当前位置: X-MOL 学术IEEE Trans. Pattern Anal. Mach. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Self-Supervised Deep Monocular Depth Estimation With Ambiguity Boosting.
IEEE Transactions on Pattern Analysis and Machine Intelligence ( IF 20.8 ) Pub Date : 2022-11-07 , DOI: 10.1109/tpami.2021.3124079
Juan Luis Gonzalez Bello 1 , Munchurl Kim 1
Affiliation  

We propose a novel two-stage training strategy with ambiguity boosting for the self-supervised learning of single view depths from stereo images. Our proposed two-stage learning strategy first aims to obtain a coarse depth prior by training an auto-encoder network for a stereoscopic view synthesis task. This prior knowledge is then boosted and used to self-supervise the model in the second stage of training in our novel ambiguity boosting loss. Our ambiguity boosting loss is a confidence-guided type of data augmentation loss that improves the accuracy and consistency of generated depth maps under several transformations of the single-image input. To show the benefits of the proposed two-stage training strategy with boosting, our two previous depth estimation (DE) networks, one with t-shaped adaptive kernels and the other with exponential disparity volumes, are extended with our new learning strategy, referred to as DBoosterNet-t and DBoosterNet-e, respectively. Our self-supervised DBoosterNets are competitive, and in some cases even better, compared to the most recent supervised SOTA methods, and are remarkably superior to the previous self-supervised methods for monocular DE on the challenging KITTI dataset. We present intensive experimental results, showing the efficacy of our method for the self-supervised monocular DE task.

中文翻译:

具有模糊度增强的自监督深度单目深度估计。

我们提出了一种新颖的具有模糊度提升的两阶段训练策略,用于从立体图像中进行单视图深度的自监督学习。我们提出的两阶段学习策略首先旨在通过为立体视图合成任务训练自动编码器网络来获得粗略的先验深度。然后,在我们新颖的歧义增强损失中,该先验知识被增强并用于在训练的第二阶段自我监督模型。我们的模糊度增强损失是一种置信度引导类型的数据增强损失,它提高了在单图像输入的多次变换下生成的深度图的准确性和一致性。为了展示所提出的两阶段训练策略与提升的好处,我们之前的两个深度估计(DE)网络,一个具有 t 形自适应内核,另一个具有指数视差量,分别使用我们的新学习策略进行扩展,分别称为 DBoosterNet-t 和 DBoosterNet-e。与最近的监督 SOTA 方法相比,我们的自监督 DBoosterNet 具有竞争力,在某些情况下甚至更好,并且在具有挑战性的 KITTI 数据集上明显优于以前用于单目 DE 的自监督方法。我们展示了密集的实验结果,展示了我们的方法对自我监督单目 DE 任务的有效性。并且明显优于以前在具有挑战性的 KITTI 数据集上用于单目 DE 的自我监督方法。我们展示了密集的实验结果,展示了我们的方法对自我监督单目 DE 任务的有效性。并且明显优于以前在具有挑战性的 KITTI 数据集上用于单目 DE 的自我监督方法。我们展示了密集的实验结果,展示了我们的方法对自我监督单目 DE 任务的有效性。
更新日期:2021-11-02
down
wechat
bug