中文
相关论文

相关论文: CityGen: Structure-Guided City-Style Synthesis for…

200 篇论文

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Javier Montalvo , Roberto Alcover-Couso , Pablo Carballeira , Álvaro García-Martín , Juan C. SanMiguel , Marcos Escudero-Viñolo

Driving scene parsing is critical for autonomous vehicles to operate reliably in complex real-world traffic environments. To reduce the reliance on costly pixel-level annotations, synthetic datasets with automatically generated labels have…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Jiahe Fan , Xiao Ma , Sergey Vityazev , George Giakos , Shaolong Shu , Rui Fan

Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory observations, limiting…

计算机视觉与模式识别 · 计算机科学 2025-12-05 Shijie Chen , Peixi Peng

Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the 3D object layout. However, those models are trained on…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Yunsong Zhou , Michael Simon , Zhenghao Peng , Sicheng Mo , Hongzi Zhu , Minyi Guo , Bolei Zhou

The need for large amounts of training and validation data is a huge concern in scaling AI algorithms for autonomous driving. Semantic Image Synthesis (SIS), or label-to-image translation, promises to address this issue by translating…

计算机视觉与模式识别 · 计算机科学 2023-05-18 George Eskandar , Diandian Guo , Karim Guirguis , Bin Yang

The rapid advancement of autonomous driving (AD) technologies has outpaced the development of robust safety evaluation methods. Conventional testing relies on exposing AD systems to vast numbers of real-world traffic scenes -- a brute-force…

Artificial intelligence (AI) approaches nowadays have gained remarkable success in single-modality-dominated remote sensing (RS) applications, especially with an emphasis on individual urban environments (e.g., single cities or regions).…

计算机视觉与模式识别 · 计算机科学 2023-10-04 Danfeng Hong , Bing Zhang , Hao Li , Yuxuan Li , Jing Yao , Chenyu Li , Martin Werner , Jocelyn Chanussot , Alexander Zipf , Xiao Xiang Zhu

Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories,…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Henry Che , Jingkang Wang , Yun Chen , Ze Yang , Sivabalan Manivasagam , Raquel Urtasun

The development of autonomous vehicles requires having access to a large amount of data in the concerning driving scenarios. However, manual annotation of such driving scenarios is costly and subject to the errors in the rule-based…

机器学习 · 计算机科学 2020-09-29 Fazeleh S. Hoseini , Sadegh Rahrovani , Morteza Haghir Chehreghani

Recent advancements in generative AI, particularly diffusion-based image editing, have enabled the transformation of images into highly realistic scenes using only text instructions. This technology offers significant potential for…

计算机视觉与模式识别 · 计算机科学 2024-11-04 Naufal Suryanto , Andro Aprila Adiputra , Ahmada Yusril Kadiptya , Thi-Thu-Huong Le , Derry Pratama , Yongsu Kim , Howon Kim

A domain adaptation method for urban scene segmentation is proposed in this work. We develop a fully convolutional tri-branch network, where two branches assign pseudo labels to images in the unlabeled target domain while the third branch…

计算机视觉与模式识别 · 计算机科学 2018-02-28 Junting Zhang , Chen Liang , C. -C. Jay Kuo

Understanding the traffic dynamics in networks is a core capability for automated systems to monitor and analyze networking behaviors, reducing expensive human efforts and economic risks through tasks such as traffic classification,…

机器学习 · 计算机科学 2024-12-31 Jiawei Zhou , Woojeong Kim , Zhiying Xu , Alexander M. Rush , Minlan Yu

Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set would not achieve satisfactory performance due to dataset…

计算机视觉与模式识别 · 计算机科学 2017-04-28 Yi-Hsin Chen , Wei-Yu Chen , Yu-Ting Chen , Bo-Cheng Tsai , Yu-Chiang Frank Wang , Min Sun

Diverse and realistic traffic scenarios are crucial for evaluating the AI safety of autonomous driving systems in simulation. This work introduces a data-driven method called TrafficGen for traffic scenario generation. It learns from the…

机器人学 · 计算机科学 2023-03-07 Lan Feng , Quanyi Li , Zhenghao Peng , Shuhan Tan , Bolei Zhou

High Definition (HD) maps are maps with precise definitions of road lanes with rich semantics of the traffic rules. They are critical for several key stages in an autonomous driving system, including motion forecasting and planning.…

计算机视觉与模式识别 · 计算机科学 2021-06-29 Lu Mi , Hang Zhao , Charlie Nash , Xiaohan Jin , Jiyang Gao , Chen Sun , Cordelia Schmid , Nir Shavit , Yuning Chai , Dragomir Anguelov

Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Shangjin Zhai , Zhichao Ye , Jialin Liu , Weijian Xie , Jiaqi Hu , Zhen Peng , Hua Xue , Danpeng Chen , Xiaomeng Wang , Lei Yang , Nan Wang , Haomin Liu , Guofeng Zhang

With the rapid advances in generative adversarial networks (GANs), the visual quality of synthesised scenes keeps improving, including for complex urban scenes with applications to automated driving. We address in this work a continual…

计算机视觉与模式识别 · 计算机科学 2022-05-03 Himalaya Jain , Tuan-Hung Vu , Patrick Pérez , Matthieu Cord

Generalization performance of trained computer vision systems that use computer graphics (CG) generated data is not yet effective due to the concept of 'domain-shift' between virtual and real data. Although simulated data augmented with a…

计算机视觉与模式识别 · 计算机科学 2017-07-10 V S R Veeravasarapu , Constantin Rothkopf , Ramesh Visvanathan

Traditional decision and planning frameworks for self-driving vehicles (SDVs) scale poorly in new scenarios, thus they require tedious hand-tuning of rules and parameters to maintain acceptable performance in all foreseeable cases.…

机器人学 · 计算机科学 2021-08-02 Peide Cai , Hengli Wang , Yuxiang Sun , Ming Liu

Accurate lane detection, a crucial enabler for autonomous driving, currently relies on obtaining a large and diverse labeled training dataset. In this work, we explore learning from abundant, randomly generated synthetic data, together with…

计算机视觉与模式识别 · 计算机科学 2020-11-10 Noa Garnett , Roy Uziel , Netalee Efrat , Dan Levi