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.

自监督的单目深度估计任务中，离散视差预测已被证明比常规连续方法获得更高质量深度图。然而，当前的离散化策略通常以手工制定且刚性的方式将场景的深度范围划分为箱子，限制了模型的性能。本文提出了一种可学习模块，自适应离散视差体积（ADDV），能够动态感知不同 RGB 图像中的深度分布，并为其生成自适应箱子。该模块可以集成到现有的 CNN 架构中，使网络能够为箱子生成代表性数值和其概率分布。此外，我们引入了新的训练策略 - 均一化和锐化 - 通过损失项和温度参数，以在自监督条件下提供规范化，防止模型退化或崩溃。实证结果表明，ADDV 能有效处理全局信息，在各种场景中生成适当的箱子，并与手工方法相比产生更高质量的深度图。