Frequency-Aware Self-Supervised Monocular Depth Estimation
This work addresses fundamental issues in depth estimation for computer vision applications, but it is incremental as it enhances existing models rather than introducing a new paradigm.
The paper tackles the problem of incorrect supervision in photometric loss for self-supervised monocular depth estimation by proposing Ambiguity-Masking and a frequency-adaptive Gaussian low-pass filter, resulting in performance boosts for existing models without extra inference computation.
We present two versatile methods to generally enhance self-supervised monocular depth estimation (MDE) models. The high generalizability of our methods is achieved by solving the fundamental and ubiquitous problems in photometric loss function. In particular, from the perspective of spatial frequency, we first propose Ambiguity-Masking to suppress the incorrect supervision under photometric loss at specific object boundaries, the cause of which could be traced to pixel-level ambiguity. Second, we present a novel frequency-adaptive Gaussian low-pass filter, designed to robustify the photometric loss in high-frequency regions. We are the first to propose blurring images to improve depth estimators with an interpretable analysis. Both modules are lightweight, adding no parameters and no need to manually change the network structures. Experiments show that our methods provide performance boosts to a large number of existing models, including those who claimed state-of-the-art, while introducing no extra inference computation at all.