Semi-Supervised Learning of Monocular Depth Estimation via Consistency Regularization with K-way Disjoint Masking

12/21/2022
by   Jongbeom Baek, et al.
0

Semi-Supervised Learning (SSL) has recently accomplished successful achievements in various fields such as image classification, object detection, and semantic segmentation, which typically require a lot of labour to construct ground-truth. Especially in the depth estimation task, annotating training data is very costly and time-consuming, and thus recent SSL regime seems an attractive solution. In this paper, for the first time, we introduce a novel framework for semi-supervised learning of monocular depth estimation networks, using consistency regularization to mitigate the reliance on large ground-truth depth data. We propose a novel data augmentation approach, called K-way disjoint masking, which allows the network for learning how to reconstruct invisible regions so that the model not only becomes robust to perturbations but also generates globally consistent output depth maps. Experiments on the KITTI and NYU-Depth-v2 datasets demonstrate the effectiveness of each component in our pipeline, robustness to the use of fewer and fewer annotated images, and superior results compared to other state-of-the-art, semi-supervised methods for monocular depth estimation. Our code is available at https://github.com/KU-CVLAB/MaskingDepth.

READ FULL TEXT

page 2

page 3

page 4

page 6

page 10

page 11

page 14

research
09/23/2021

Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data

Depth estimation from a single image is an active research topic in comp...
research
03/18/2022

Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation

We propose a semi-supervised learning framework for monocular depth esti...
research
09/02/2020

Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training

In this work, we propose a novel single-shot and keypoints-based framewo...
research
08/28/2023

Semi-Supervised Semantic Depth Estimation using Symbiotic Transformer and NearFarMix Augmentation

In computer vision, depth estimation is crucial for domains like robotic...
research
08/06/2019

Semi-Supervised Adversarial Monocular Depth Estimation

In this paper, we address the problem of monocular depth estimation when...
research
04/13/2022

Does depth estimation help object detection?

Ground-truth depth, when combined with color data, helps improve object ...
research
07/13/2022

Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometry

Supervised learning depth estimation methods can achieve good performanc...

Please sign up or login with your details

Forgot password? Click here to reset