paper-with-me

홈 › Papers

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

2023-12-19 · Jose L. Gómez, Manuel Silva, Antonio Seoane, Agnès Borrás, Mario Noriega, Germán Ros, Jose A. Iglesias-Guitian, Antonio M. López

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).

📄 PDF Abstract BibTeX arXiv:2312.12176

Code (0)

등록된 구현이 없습니다.

Tasks

AllDomain AdaptationInstance SegmentationSegmentationSemantic SegmentationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

SGD with Coordinate Sampling: Theory and Practice

2021-05-25 · Rémi Leluc, François Portier

While classical forms of stochastic gradient descent algorithm treat the different coordinates in the same way, a framework allowing for adaptive (non uniform) coordinate sampling is developed to leverage structure in da…

Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts

2023-05-11 · Zhaoyang Zhang, Yantao Shen, Kunyu Shi, Zhaowei Cai 외

We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Mus…

Language ModelingLanguage Modelling

UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation

2024-05-15 · Yachan Guo, Yi Xiao, Danna Xue, Jose Luis Gomez Zurita 외

Instance segmentation is crucial for autonomous driving but is hindered by the lack of annotated real-world data due to expensive labeling costs. Unsupervised Domain Adaptation (UDA) offers a solution by transferring kno…

Autonomous DrivingDomain AdaptationInstance Segmentationobject-detection+4

GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation

2022-07-20 · Cristiano Saltori, Evgeny Krivosheev, Stéphane Lathuilière, Nicu Sebe 외

3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when handling dynamic scenes. This can signif…

Autonomous DrivingDomain AdaptationOnline unsupervised domain adaptationPoint Cloud Segmentation+3

Synthetic Data for Deep Learning

2019-09-25 · Sergey I. Nikolenko

Synthetic data is an increasingly popular tool for training deep learning models, especially in computer vision but also in other areas. In this work, we attempt to provide a comprehensive survey of the various direction…

Autonomous DrivingDeep LearningDomain AdaptationOptical Flow Estimation+2