Unsupervised Domain Adaptation for Depth Prediction from Images

09/09/2019
by   Alessio Tonioni, et al.
0

State-of-the-art approaches to infer dense depth measurements from images rely on CNNs trained end-to-end on a vast amount of data. However, these approaches suffer a drastic drop in accuracy when dealing with environments much different in appearance and/or context from those observed at training time. This domain shift issue is usually addressed by fine-tuning on smaller sets of images from the target domain annotated with depth labels. Unfortunately, relying on such supervised labeling is seldom feasible in most practical settings. Therefore, we propose an unsupervised domain adaptation technique which does not require groundtruth labels. Our method relies only on image pairs and leverages on classical stereo algorithms to produce disparity measurements alongside with confidence estimators to assess upon their reliability. We propose to fine-tune both depth-from-stereo as well as depth-from-mono architectures by a novel confidence-guided loss function that handles the measured disparities as noisy labels weighted according to the estimated confidence. Extensive experimental results based on standard datasets and evaluation protocols prove that our technique can address effectively the domain shift issue with both stereo and monocular depth prediction architectures and outperforms other state-of-the-art unsupervised loss functions that may be alternatively deployed to pursue domain adaptation.

READ FULL TEXT

page 4

page 6

page 11

page 12

page 14

research
01/27/2020

Learning Transferrable Representations for Unsupervised Domain Adaptation

Supervised learning with large scale labelled datasets and deep layered ...
research
12/15/2017

Unsupervised Domain Adaptation for 3D Keypoint Prediction from a Single Depth Scan

In this paper, we introduce a novel unsupervised domain adaptation techn...
research
05/24/2019

Guided Stereo Matching

Stereo is a prominent technique to infer dense depth maps from images, a...
research
09/19/2022

3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling

For monocular depth estimation, acquiring ground truths for real data is...
research
07/20/2021

Self-Supervised Domain Adaptation for Diabetic Retinopathy Grading using Vessel Image Reconstruction

This paper investigates the problem of domain adaptation for diabetic re...
research
03/09/2022

Unsupervised Domain Adaptation across FMCW Radar Configurations Using Margin Disparity Discrepancy

Commercial radar sensing is gaining relevance and machine learning algor...
research
03/04/2019

Unsupervised Cross-spectral Stereo Matching by Learning to Synthesize

Unsupervised cross-spectral stereo matching aims at recovering disparity...

Please sign up or login with your details

Forgot password? Click here to reset