中文
相关论文

相关论文: Para-Lane: Multi-Lane Dataset Registering Parallel…

200 篇论文

Novel View Synthesis (NVS), which tries to produce a realistic image at the target view given source view images and their corresponding poses, is a fundamental problem in 3D Vision. As this task is heavily under-constrained, some recent…

计算机视觉与模式识别 · 计算机科学 2023-12-15 Shijie Li , Farhad G. Zanjani , Haitam Ben Yahia , Yuki M. Asano , Juergen Gall , Amirhossein Habibian

Photorealistic avatars of human faces have come a long way in recent years, yet research along this area is limited by a lack of publicly available, high-quality datasets covering both, dense multi-view camera captures, and rich facial…

Gaussian Splatting (GS) and Neural Radiance Fields (NeRF) are two groundbreaking technologies that have revolutionized the field of Novel View Synthesis (NVS), enabling immersive photorealistic rendering and user experiences by synthesizing…

计算机视觉与模式识别 · 计算机科学 2025-01-15 Yuhang Zhang , Joshua Maraval , Zhengyu Zhang , Nicolas Ramin , Shishun Tian , Lu Zhang

Novel View Synthesis (NVS) for street scenes play a critical role in the autonomous driving simulation. The current mainstream technique to achieve it is neural rendering, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting…

计算机视觉与模式识别 · 计算机科学 2024-04-01 Zhongrui Yu , Haoran Wang , Jinze Yang , Hanzhang Wang , Zeke Xie , Yunfeng Cai , Jiale Cao , Zhong Ji , Mingming Sun

Remote sensing novel view synthesis (NVS) offers significant potential for 3D interpretation of remote sensing scenes, with important applications in urban planning and environmental monitoring. However, remote sensing scenes frequently…

计算机视觉与模式识别 · 计算机科学 2026-01-19 Jiaming Kang , Keyan Chen , Zhengxia Zou , Zhenwei Shi

Novel view synthesis (NVS) of multi-human scenes imposes challenges due to the complex inter-human occlusions. Layered representations handle the complexities by dividing the scene into multi-layered radiance fields, however, they are…

计算机视觉与模式识别 · 计算机科学 2023-09-22 Youssef Abdelkareem , Shady Shehata , Fakhri Karray

Existing state-of-the-art novel view synthesis methods rely on either fairly accurate 3D geometry estimation or sampling of the entire space for neural volumetric rendering, which limit the overall efficiency. In order to improve the…

计算机视觉与模式识别 · 计算机科学 2022-04-08 Yuemei Zhou , Tao Yu , Zerong Zheng , Ying Fu , Yebin Liu

Reliable and accurate lane detection has been a long-standing problem in the field of autonomous driving. In recent years, many approaches have been developed that use images (or videos) as input and reason in image space. In this paper we…

计算机视觉与模式识别 · 计算机科学 2019-05-07 Min Bai , Gellert Mattyus , Namdar Homayounfar , Shenlong Wang , Shrinidhi Kowshika Lakshmikanth , Raquel Urtasun

Realistic view extrapolation is critical for closed-loop simulation in autonomous driving, yet it remains a significant challenge for current Novel View Synthesis (NVS) methods, which often produce distorted and inconsistent images beyond…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Kaiyuan Tan , Yingying Shen , Haiyang Sun , Bing Wang , Guang Chen , Hangjun Ye

Retrospective novel view synthesis (NVS) of dynamic scenes is fundamental to applications such as sports. Recent dynamic 3D Gaussian Splatting (3DGS) approaches introduce temporally coupled formulations to enforce motion coherence across…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Yunxiao Zhang , Suryansh Kumar

Existing lane-level simulation road network generation is labor-intensive, resource-demanding, and costly due to the need for large-scale data collection and manual post-editing. To overcome these limitations, we propose automatically…

多媒体 · 计算机科学 2025-09-04 Liang Xie , Wenke Huang

3D visual perception tasks based on multi-camera images are essential for autonomous driving systems. Latest work in this field performs 3D object detection by leveraging multi-view images as an input and iteratively enhancing object…

计算机视觉与模式识别 · 计算机科学 2023-07-31 Jongwoo Park , Apoorv Singh , Varun Bankiti

We address the problem of novel view synthesis (NVS) from a few sparse source view images. Conventional image-based rendering methods estimate scene geometry and synthesize novel views in two separate steps. However, erroneous geometry…

计算机视觉与模式识别 · 计算机科学 2021-04-06 Yujiao Shi , Hongdong Li , Xin Yu

Synthesizing free-view photo-realistic images is an important task in multimedia. With the development of advanced driver assistance systems~(ADAS) and their applications in autonomous vehicles, experimenting with different scenarios…

计算机视觉与模式识别 · 计算机科学 2022-05-13 Zhuopeng Li , Lu Li , Zeyu Ma , Ping Zhang , Junbo Chen , Jianke Zhu

Novel view synthesis (NVS) is a challenging task requiring systems to generate photorealistic images of scenes from new viewpoints, where both quality and speed are important for applications. Previous image-based rendering (IBR) methods…

计算机视觉与模式识别 · 计算机科学 2022-08-08 Ang Cao , Chris Rockwell , Justin Johnson

Autonomous driving system development is critically dependent on the ability to replay complex and diverse traffic scenarios in simulation. In such scenarios, the ability to accurately simulate the vehicle sensors such as cameras, lidar or…

计算机视觉与模式识别 · 计算机科学 2020-06-26 Zhenpei Yang , Yuning Chai , Dragomir Anguelov , Yin Zhou , Pei Sun , Dumitru Erhan , Sean Rafferty , Henrik Kretzschmar

Existing reconstruction-based novel view synthesis methods for driving scenes focus on synthesizing camera views along the recorded trajectory of the ego vehicle. Their image rendering performance will severely degrade on viewpoints falling…

计算机视觉与模式识别 · 计算机科学 2024-10-24 Qitai Wang , Lue Fan , Yuqi Wang , Yuntao Chen , Zhaoxiang Zhang

One of the main factors that contributed to the large advances in autonomous driving is the advent of deep learning. For safer self-driving vehicles, one of the problems that has yet to be solved completely is lane detection. Since methods…

计算机视觉与模式识别 · 计算机科学 2020-07-15 Lucas Tabelini , Rodrigo Berriel , Thiago M. Paixão , Claudine Badue , Alberto F. De Souza , Thiago Oliveira-Santos

Lane detection is to detect lanes on the road and provide the accurate location and shape of each lane. It severs as one of the key techniques to enable modern assisted and autonomous driving systems. However, several unique properties of…

计算机视觉与模式识别 · 计算机科学 2018-07-06 Ze Wang , Weiqiang Ren , Qiang Qiu

Novel view synthesis is a challenging problem in computer vision and robotics. Different from the existing works, which need the reference images or 3D models of the scene to generate images under novel views, we propose a novel paradigm to…

计算机视觉与模式识别 · 计算机科学 2020-10-23 Xiang Guo , Bo Li , Yuchao Dai , Tongxin Zhang , Hui Deng