Adaptive Discrete Disparity Volume for Self-supervised Monocular Depth Estimation
This work addresses a bottleneck in self-supervised depth estimation for computer vision applications, offering an incremental improvement over existing discretization strategies.
The paper tackles the problem of rigid depth binning in self-supervised monocular depth estimation by proposing an Adaptive Discrete Disparity Volume (ADDV) module that dynamically generates adaptive bins, resulting in higher quality depth maps compared to handcrafted methods.
In self-supervised monocular depth estimation tasks, discrete disparity prediction has been proven to attain higher quality depth maps than common continuous methods. However, current discretization strategies often divide depth ranges of scenes into bins in a handcrafted and rigid manner, limiting model performance. In this paper, we propose a learnable module, Adaptive Discrete Disparity Volume (ADDV), which is capable of dynamically sensing depth distributions in different RGB images and generating adaptive bins for them. Without any extra supervision, this module can be integrated into existing CNN architectures, allowing networks to produce representative values for bins and a probability volume over them. Furthermore, we introduce novel training strategies - uniformizing and sharpening - through a loss term and temperature parameter, respectively, to provide regularizations under self-supervised conditions, preventing model degradation or collapse. Empirical results demonstrate that ADDV effectively processes global information, generating appropriate bins for various scenes and producing higher quality depth maps compared to handcrafted methods.