中文
相关论文

相关论文: RA-NeRF: Robust Neural Radiance Field Reconstructi…

200 篇论文

Neural surface reconstruction relies heavily on accurate camera poses as input. Despite utilizing advanced pose estimators like COLMAP or ARKit, camera poses can still be noisy. Existing pose-NeRF joint optimization methods handle poses…

计算机视觉与模式识别 · 计算机科学 2024-11-22 Yi Gu , Dongjun Ye , Zhaorui Wang , Jiaxu Wang , Jiahang Cao , Renjing Xu

Neural radiance fields (NeRF) is a promising approach for generating photorealistic images and representing complex scenes. However, when processing data sequentially, it can suffer from catastrophic forgetting, where previous data is…

计算机视觉与模式识别 · 计算机科学 2023-12-12 Letian Zhang , Ming Li , Chen Chen , Jie Xu

We present a parallelized optimization method based on fast Neural Radiance Fields (NeRF) for estimating 6-DoF pose of a camera with respect to an object or scene. Given a single observed RGB image of the target, we can predict the…

计算机视觉与模式识别 · 计算机科学 2023-03-13 Yunzhi Lin , Thomas Müller , Jonathan Tremblay , Bowen Wen , Stephen Tyree , Alex Evans , Patricio A. Vela , Stan Birchfield

Neural Radiance Fields (NeRF) achieves impressive novel view rendering performance by learning implicit 3D representation from sparse view images. However, it is difficult to reconstruct a sharp NeRF from blurry input that often occurs in…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Yunshan Qi , Jia Li , Yifan Zhao , Yu Zhang , Lin Zhu

Obtaining a better knowledge of the current state and behavior of objects orbiting Earth has proven to be essential for a range of applications such as active debris removal, in-orbit maintenance, or anomaly detection. 3D models represent a…

计算机视觉与模式识别 · 计算机科学 2025-06-26 Clément Forray , Pauline Delporte , Nicolas Delaygue , Florence Genin , Dawa Derksen

The reliance on accurate camera poses is a significant barrier to the widespread deployment of Neural Radiance Fields (NeRF) models for 3D reconstruction and SLAM tasks. The existing method introduces monocular depth priors to jointly…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Zhen Tan , Zongtan Zhou , Yangbing Ge , Zi Wang , Xieyuanli Chen , Dewen Hu

Neural Radiance Field (NeRF) has exhibited outstanding three-dimensional (3D) reconstruction quality via the novel view synthesis from multi-view images and paired calibrated camera parameters. However, previous NeRF-based systems have been…

计算机视觉与模式识别 · 计算机科学 2023-03-10 Dogyoon Lee , Minhyeok Lee , Chajin Shin , Sangyoun Lee

Neural Radiance Fields (NeRF) have received considerable attention recently, due to its impressive capability in photo-realistic 3D reconstruction and novel view synthesis, given a set of posed camera images. Earlier work usually assumes…

计算机视觉与模式识别 · 计算机科学 2023-06-27 Peng Wang , Lingzhe Zhao , Ruijie Ma , Peidong Liu

We present VERF, a collection of two methods (VERF-PnP and VERF-Light) for providing runtime assurance on the correctness of a camera pose estimate of a monocular camera without relying on direct depth measurements. We leverage the ability…

机器人学 · 计算机科学 2023-08-14 Dominic Maggio , Courtney Mario , Luca Carlone

Neural Radiance Fields (NeRF) have recently demonstrated photo-realistic results for the task of novel view synthesis. In this paper, we propose to apply novel view synthesis to the robot relocalization problem: we demonstrate improvement…

计算机视觉与模式识别 · 计算机科学 2021-10-14 Arthur Moreau , Nathan Piasco , Dzmitry Tsishkou , Bogdan Stanciulescu , Arnaud de La Fortelle

Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing time. In this paper, we present EfficientNeRF as an…

计算机视觉与模式识别 · 计算机科学 2022-06-03 Tao Hu , Shu Liu , Yilun Chen , Tiancheng Shen , Jiaya Jia

Neural Radiance Fields (NeRF) use multi-view images for 3D scene representation, demonstrating remarkable performance. As one of the primary sources of multi-view images, multi-camera systems encounter challenges such as varying intrinsic…

计算机视觉与模式识别 · 计算机科学 2024-12-09 Yu Gao , Lutong Su , Hao Liang , Yufeng Yue , Yi Yang , Mengyin Fu

Reconstructing from multi-view images is a longstanding problem in 3D vision, where neural radiance fields (NeRFs) have shown great potential and get realistic rendered images of novel views. Currently, most NeRF methods either require…

计算机视觉与模式识别 · 计算机科学 2025-05-06 Xin Wen , Xuening Zhu , Renjiao Yi , Zhifeng Wang , Chenyang Zhu , Kai Xu

Several variants of Neural Radiance Fields (NeRFs) have significantly improved the accuracy of synthesized images and surface reconstruction of 3D scenes/objects. In all of these methods, a key characteristic is that none can train the…

计算机视觉与模式识别 · 计算机科学 2025-06-11 Gonçalo Dias Pais , Valter Piedade , Moitreya Chatterjee , Marcus Greiff , Pedro Miraldo

Neural Radiance Fields (NeRF) coupled with GANs represent a promising direction in the area of 3D reconstruction from a single view, owing to their ability to efficiently model arbitrary topologies. Recent work in this area, however, has…

计算机视觉与模式识别 · 计算机科学 2023-03-21 Dario Pavllo , David Joseph Tan , Marie-Julie Rakotosaona , Federico Tombari

Neural rendering techniques combining machine learning with geometric reasoning have arisen as one of the most promising approaches for synthesizing novel views of a scene from a sparse set of images. Among these, stands out the Neural…

计算机视觉与模式识别 · 计算机科学 2020-12-01 Albert Pumarola , Enric Corona , Gerard Pons-Moll , Francesc Moreno-Noguer

When a camera travels across a 3D world, only a fraction of pixel value changes; an event-based camera observes the change as sparse events. How can we utilize sparse events for efficient recovery of the camera pose? We show that we can…

计算机视觉与模式识别 · 计算机科学 2023-04-11 Mana Masuda , Yusuke Sekikawa , Hideo Saito

Neural Radiance Fields (NeRF) have demonstrated very impressive performance in novel view synthesis via implicitly modelling 3D representations from multi-view 2D images. However, most existing studies train NeRF models with either…

计算机视觉与模式识别 · 计算机科学 2023-06-13 Jiahui Zhang , Fangneng Zhan , Rongliang Wu , Yingchen Yu , Wenqing Zhang , Bai Song , Xiaoqin Zhang , Shijian Lu

We present a novel optimization algorithm called DroNeRF for the autonomous positioning of monocular camera drones around an object for real-time 3D reconstruction using only a few images. Neural Radiance Fields or NeRF, is a novel view…

机器人学 · 计算机科学 2023-08-08 Dipam Patel , Phu Pham , Aniket Bera

Existing volumetric neural rendering techniques, such as Neural Radiance Fields (NeRF), face limitations in synthesizing high-quality novel views when the camera poses of input images are imperfect. To address this issue, we propose a novel…

计算机视觉与模式识别 · 计算机科学 2023-10-17 Hongyu Fu , Xin Yu , Lincheng Li , Li Zhang