All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gómez, Jose L., Silva, Manuel, Seoane, Antonio, Borrás, Agnès, Noriega, Mario, Ros, Germán, Iglesias-Guitian, Jose A., López, Antonio M.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908336888217600
author Gómez, Jose L.
Silva, Manuel
Seoane, Antonio
Borrás, Agnès
Noriega, Mario
Ros, Germán
Iglesias-Guitian, Jose A.
López, Antonio M.
author_facet Gómez, Jose L.
Silva, Manuel
Seoane, Antonio
Borrás, Agnès
Noriega, Mario
Ros, Germán
Iglesias-Guitian, Jose A.
López, Antonio M.
contents We introduce UrbanSyn, a photorealistic dataset acquired through semi-procedurally generated synthetic urban driving scenarios. Developed using high-quality geometry and materials, UrbanSyn provides pixel-level ground truth, including depth, semantic segmentation, and instance segmentation with object bounding boxes and occlusion degree. It complements GTAV and Synscapes datasets to form what we coin as the 'Three Musketeers'. We demonstrate the value of the Three Musketeers in unsupervised domain adaptation for image semantic segmentation. Results on real-world datasets, Cityscapes, Mapillary Vistas, and BDD100K, establish new benchmarks, largely attributed to UrbanSyn. We make UrbanSyn openly and freely accessible (www.urbansyn.org).
format Preprint
id arxiv_https___arxiv_org_abs_2312_12176
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes
Gómez, Jose L.
Silva, Manuel
Seoane, Antonio
Borrás, Agnès
Noriega, Mario
Ros, Germán
Iglesias-Guitian, Jose A.
López, Antonio M.
Computer Vision and Pattern Recognition
We introduce UrbanSyn, a photorealistic dataset acquired through semi-procedurally generated synthetic urban driving scenarios. Developed using high-quality geometry and materials, UrbanSyn provides pixel-level ground truth, including depth, semantic segmentation, and instance segmentation with object bounding boxes and occlusion degree. It complements GTAV and Synscapes datasets to form what we coin as the 'Three Musketeers'. We demonstrate the value of the Three Musketeers in unsupervised domain adaptation for image semantic segmentation. Results on real-world datasets, Cityscapes, Mapillary Vistas, and BDD100K, establish new benchmarks, largely attributed to UrbanSyn. We make UrbanSyn openly and freely accessible (www.urbansyn.org).
title All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.12176