Mapillary Planet-Scale Depth Dataset

Manuel López Antequera, Pau Gargallo, Markus Hofinger, Samuel Rota Bulò, Yubin Kuang, Peter Kontschieder

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

Learning-based methods produce remarkable results on single image depth tasks when trained on well-established benchmarks, however, there is a large gap from these benchmarks to real-world performance that is usually obscured by the common practice of fine-tuning on the target dataset. We introduce a new depth dataset that is an order of magnitude larger than previous datasets, but more importantly, contains an unprecedented gamut of locations, camera models and scene types while offering metric depth (not just up-to-scale). Additionally, we investigate the problem of training single image depth networks using images captured with many different cameras, validating an existing approach and proposing a simpler alternative. With our contributions we achieve excellent results on challenging benchmarks before fine-tuning, and set the state of the art on the popular KITTI dataset after fine-tuning.

The dataset is available at mapillary.com/dataset/depth.
Original languageEnglish
Title of host publicationComputer Vision – ECCV 2020
Subtitle of host publication16th European Conference, 2020, Proceedings
EditorsAndrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm
Pages589-604
Number of pages16
Volume12347
ISBN (Electronic)978-3-030-58536-5
DOIs
Publication statusPublished - 1 Jan 2020
Event16th European Conference on Computer Vision: ECCV 2020 - Virtual, Glasgow, United Kingdom
Duration: 23 Aug 202028 Aug 2020

Publication series

NameLecture Notes in Computer Science
Volume12347
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference16th European Conference on Computer Vision
Abbreviated titleECCV 2020
Country/TerritoryUnited Kingdom
CityVirtual, Glasgow
Period23/08/2028/08/20

Fingerprint

Dive into the research topics of 'Mapillary Planet-Scale Depth Dataset'. Together they form a unique fingerprint.

Cite this