DeepAI AI Chat
Log In Sign Up

Frequency-Aware Self-Supervised Monocular Depth Estimation

by   Xingyu Chen, et al.
Peking University

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.


page 3

page 4

page 7


Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes

Self-supervised deep learning methods have leveraged stereo images for t...

Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem

Self-supervised monocular depth estimation (MDE) models universally suff...

Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation

Self-supervised methods play an increasingly important role in monocular...

Calibrating Self-supervised Monocular Depth Estimation

In the recent years, many methods demonstrated the ability of neural net...

Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter

This paper presents an open and comprehensive framework to systematicall...

BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation

Due to the rise of spherical cameras, monocular 360 depth estimation bec...

Edge-Guided Occlusion Fading Reduction for a Light-Weighted Self-Supervised Monocular Depth Estimation

Self-supervised monocular depth estimation methods generally suffer the ...

Code Repositories


[WACV2023] Frequency Aware Self-supervised Depth Estimation

view repo