Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation

03/11/2019
by   Andrea Pilzer, et al.
0

Nowadays, the majority of state of the art monocular depth estimation techniques are based on supervised deep learning models. However, collecting RGB images with associated depth maps is a very time consuming procedure. Therefore, recent works have proposed deep architectures for addressing the monocular depth prediction task as a reconstruction problem, thus avoiding the need of collecting ground-truth depth. Following these works, we propose a novel self-supervised deep model for estimating depth maps. Our framework exploits two main strategies: refinement via cycle-inconsistency and distillation. Specifically, first a student network is trained to predict a disparity map such as to recover from a frame in a camera view the associated image in the opposite view. Then, a backward cycle network is applied to the generated image to re-synthesize back the input image, estimating the opposite disparity. A third network exploits the inconsistency between the original and the reconstructed input frame in order to output a refined depth map. Finally, knowledge distillation is exploited, such as to transfer information from the refinement network to the student. Our extensive experimental evaluation demonstrate the effectiveness of the proposed framework which outperforms state of the art unsupervised methods on the KITTI benchmark.

READ FULL TEXT

page 3

page 7

page 8

research
02/20/2023

Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinement

Monocular depth estimation plays a fundamental role in computer vision. ...
research
05/18/2022

Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge

Monocular depth estimation has been extensively explored based on deep l...
research
07/28/2018

Unsupervised Adversarial Depth Estimation using Cycled Generative Networks

While recent deep monocular depth estimation approaches based on supervi...
research
09/17/2019

Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks

Recent deep monocular depth estimation approaches based on supervised re...
research
01/20/2023

FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation

The great potential of unsupervised monocular depth estimation has been ...
research
03/30/2022

Monitored Distillation for Positive Congruent Depth Completion

We propose a method to infer a dense depth map from a single image, its ...
research
11/20/2018

Double Refinement Network for Efficient Indoor Monocular Depth Estimation

Monocular Depth Estimation is an important problem of Computer Vision th...

Please sign up or login with your details

Forgot password? Click here to reset