SynerFill: A Synergistic RGB-D Image Inpainting Network via Fast Fourier Convolutions

doi:10.1109/TIV.2023.3326236

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	SynerFill: A Synergistic RGB-D Image Inpainting Network via Fast Fourier Convolutions
	Liu, Kunhua 3; Zhang, Yunqing 2; Xie, Yuting 2; Li, Leixin 2; Wang, Yutong 1; Chen, Long 1
刊名	IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
	2024
卷号	9 期号:1 页码:69-78
关键词	Image edge detection Feature extraction Point cloud compression Generators Maintenance engineering Vehicle dynamics Autonomous vehicles GAN generator discriminator SCRGB-D dataset synergistic RGB-D images inpainting
ISSN号	2379-8858
DOI	10.1109/TIV.2023.3326236
通讯作者	Chen, Long(long.chen@ia.ac.cn)
英文摘要	Map inpainting is an important technology in the production of maps for autonomous driving vehicles. In recent years, scholars have often used methods such as point cloud inpainting, RGB image inpainting, and depth inpainting to repair maps. However, these methods require high computational power and result in longer algorithmic processing times. To address this issue, we propose SynerFill, a synergistic RGB-D images inpainting method that can simultaneously inpaint RGB and depth images. We design its network architecture and loss functions, which include a generator, an RGB image discriminator, a depth image discriminator, and an edge image discriminator. Second, we collect real-world data and build a large-scale, multi-scene, multi-weather dataset called the Synthetic City RGB-D (SCRGB-D) Dataset based on 3ds Max, CARLA, and Unreal Engine 4. To verify SynerFill, we conduct experiments on the SCRGB-D dataset, DynaFill dataset, and SceneNet dataset. The experimental results show that SynerFill achieves state-of-the-art (SOTA) performance.
资助项目	National Natural Science Foundation of China[62006256] ; National Natural Science Foundation of China[62373356] ; Key Lab of Industrial Fluid Energy Conservation and Pollution Control (Qingdao University of Technology), Ministry of Education
WOS关键词	INTELLIGENT VEHICLES ; ARTIFICIAL-INTELLIGENCE ; OBJECT REMOVAL ; SEGMENTATION
WOS研究方向	Computer Science ; Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001173317800016
资助机构	National Natural Science Foundation of China ; Key Lab of Industrial Fluid Energy Conservation and Pollution Control (Qingdao University of Technology), Ministry of Education
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/58704]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Chen, Long
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Sun Yat Sen Univ, Sch Comp Sci & Engn, Guangzhou 510006, Peoples R China 3.Qingdao Univ Technol, Sch Mech & Automot Engn, Qingdao 266520, Peoples R China
推荐引用方式 GB/T 7714	Liu, Kunhua,Zhang, Yunqing,Xie, Yuting,et al. SynerFill: A Synergistic RGB-D Image Inpainting Network via Fast Fourier Convolutions[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2024,9(1):69-78.
APA	Liu, Kunhua,Zhang, Yunqing,Xie, Yuting,Li, Leixin,Wang, Yutong,&Chen, Long.(2024).SynerFill: A Synergistic RGB-D Image Inpainting Network via Fast Fourier Convolutions.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,9(1),69-78.
MLA	Liu, Kunhua,et al."SynerFill: A Synergistic RGB-D Image Inpainting Network via Fast Fourier Convolutions".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 9.1(2024):69-78.