SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation

10/03/2018
by   Sudeep Pillai, et al.
0

Recent techniques in self-supervised monocular depth estimation are approaching the performance of supervised methods, but operate in low resolution only. We show that high resolution is key towards high-fidelity self-supervised monocular depth prediction. Inspired by recent deep learning methods for Single-Image Super-Resolution, we propose a sub-pixel convolutional layer extension for depth super-resolution that accurately synthesizes high-resolution disparities from their corresponding low-resolution convolutional features. In addition, we introduce a differentiable flip-augmentation layer that accurately fuses predictions from the image and its horizontally flipped version, reducing the effect of left and right shadow regions generated in the disparity map due to occlusions. Both contributions provide significant performance gains over the state-of-the-art in self-supervised depth and pose estimation on the public KITTI benchmark. A video of our approach can be found at https://youtu.be/jKNgBeBMx0I.

READ FULL TEXT

page 1

page 3

page 5

research
09/17/2023

Deep Neighbor Layer Aggregation for Lightweight Self-Supervised Monocular Depth Estimation

With the frequent use of self-supervised monocular depth estimation in r...
research
12/08/2018

Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss

We present a novel unsupervised learning framework for single view depth...
research
07/27/2020

3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning

3D human shape and pose estimation from monocular images has been an act...
research
03/24/2021

SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing

Most monocular depth sensing methods use conventionally captured images ...
research
05/30/2023

HQDec: Self-Supervised Monocular Depth Estimation Based on a High-Quality Decoder

Decoders play significant roles in recovering scene depths. However, the...
research
09/22/2016

Is the deconvolution layer the same as a convolutional layer?

In this note, we want to focus on aspects related to two questions most ...
research
04/17/2023

360^∘ High-Resolution Depth Estimation via Uncertainty-aware Structural Knowledge Transfer

Recently, omnidirectional images (ODIs) have become increasingly popular...

Please sign up or login with your details

Forgot password? Click here to reset