Monocular Fisheye Camera Depth Estimation Using Semi-supervised Sparse Velodyne Data

03/16/2018
by   Varun Ravi Kumar, et al.
1

Near field depth estimation around a self driving car is an important function that can be achieved by four wide-angle fishey cameras having a large field of view. In this work, we explore an alternate apporach of training using sparse LIDAR data as ground truth for depth estimation for fisheye cameras.

READ FULL TEXT

page 5

page 6

page 7

page 9

page 10

page 13

research
06/27/2016

Depth Estimation from Single Image using Sparse Representations

Monocular depth estimation is an interesting and challenging problem as ...
research
04/09/2021

SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras

A 360 perception of scene geometry is essential for automated driving, n...
research
02/03/2022

Boosting Monocular Depth Estimation with Sparse Guided Points

Existing monocular depth estimation shows excellent robustness in the wi...
research
12/10/2022

Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation

Monocular Depth Estimation (MDE) is a fundamental problem in computer vi...
research
06/21/2019

Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios

This work presents an evaluation benchmark for depth estimation and comp...
research
08/27/2022

Neural Camera Models

Modern computer vision has moved beyond the domain of internet photo col...
research
07/07/2023

Depth Estimation Analysis of Orthogonally Divergent Fisheye Cameras with Distortion Removal

Stereo vision systems have become popular in computer vision application...

Please sign up or login with your details

Forgot password? Click here to reset