中文
相关论文

相关论文: UltraG-Ray: Physics-Based Gaussian Ray Casting for…

200 篇论文

X-ray is widely applied for transmission imaging due to its stronger penetration than natural light. When rendering novel view X-ray projections, existing methods mainly based on NeRF suffer from long training time and slow inference speed.…

图像与视频处理 · 电气工程与系统科学 2024-10-29 Yuanhao Cai , Yixun Liang , Jiahao Wang , Angtian Wang , Yulun Zhang , Xiaokang Yang , Zongwei Zhou , Alan Yuille

Sparse-view computed tomography (CT) reduces radiation exposure by acquiring fewer projections, making it a valuable tool in clinical scenarios where low-dose radiation is essential. However, this often results in increased noise and…

图像与视频处理 · 电气工程与系统科学 2026-04-21 Yingtai Li , Xueming Fu , Han Li , Shang Zhao , Ruiyang Jin , S. Kevin Zhou

Novel View Synthesis (NVS) aims to generate unseen views of a 3D object given a limited number of known views. Existing methods often struggle to synthesize plausible views for unobserved regions, particularly under single-view input, and…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Jinglin Liang , Zijian Zhou , Rui Huang , Shuangping Huang , Yichen Gong

Photorealistic simulators are essential for the training and evaluation of vision-centric autonomous vehicles (AVs). At their core is Novel View Synthesis (NVS), a crucial capability that generates diverse unseen viewpoints to accommodate…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Xiangyu Han , Zhen Jia , Boyi Li , Yan Wang , Boris Ivanovic , Yurong You , Lingjie Liu , Yue Wang , Marco Pavone , Chen Feng , Yiming Li

We propose a new method for realistic real-time novel-view synthesis (NVS) of large scenes. Existing neural rendering methods generate realistic results, but primarily work for small scale scenes (<50 square meters) and have difficulty at…

计算机视觉与模式识别 · 计算机科学 2023-11-10 Jeffrey Yunfan Liu , Yun Chen , Ze Yang , Jingkang Wang , Sivabalan Manivasagam , Raquel Urtasun

LiDAR novel view synthesis (NVS) has emerged as a novel task within LiDAR simulation, offering valuable simulated point cloud data from novel viewpoints to aid in autonomous driving systems. However, existing LiDAR NVS methods typically…

计算机视觉与模式识别 · 计算机科学 2025-02-06 Junzhe Jiang , Chun Gu , Yurui Chen , Li Zhang

We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Tianqi Liu , Guangcong Wang , Shoukang Hu , Liao Shen , Xinyi Ye , Yuhang Zang , Zhiguo Cao , Wei Li , Ziwei Liu

Wide Field-of-View (WFoV) reconstruction enhances 3D ultrasound imaging by providing valuable anatomical context for segmentation models and visualization. Clinical ultrasound volumes are predominantly acquired using convex probes, which…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Patris Valera , Magdalena Wysocki , Felix Duelmer , Mohammad Farid Azampour , Sebastian Herz , Stefan Wörz , Nassir Navab

Recently, 3D Gaussian Splatting (3DGS) has exceled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it faces challenges for high-resolution novel view synthesis (HRNVS) due to the coarse…

计算机视觉与模式识别 · 计算机科学 2024-12-12 Shiyun Xie , Zhiru Wang , Xu Wang , Yinghao Zhu , Chengwei Pan , Xiwang Dong

Novel view synthesis is a task of generating scenes from unseen perspectives; however, synthesizing dynamic scenes from blurry monocular videos remains an unresolved challenge that has yet to be effectively addressed. Existing novel view…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Yeon-Ji Song , Jaein Kim , Byung-Ju Kim , Byoung-Tak Zhang

Gaussian Splatting (GS) has significantly elevated scene reconstruction efficiency and novel view synthesis (NVS) accuracy compared to Neural Radiance Fields (NeRF), particularly for dynamic scenes. However, current 4D NVS methods, whether…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Fang Li , Hao Zhang , Narendra Ahuja

Neural implicit representations, including Neural Distance Fields and Neural Radiance Fields, have demonstrated significant capabilities for reconstructing surfaces with complicated geometry and topology, and generating novel views of a…

图形学 · 计算机科学 2024-02-08 Lin Gao , Jie Yang , Bo-Tao Zhang , Jia-Mu Sun , Yu-Jie Yuan , Hongbo Fu , Yu-Kun Lai

We introduce NovelGS, a diffusion model for Gaussian Splatting (GS) given sparse-view images. Recent works leverage feed-forward networks to generate pixel-aligned Gaussians, which could be fast rendered. Unfortunately, the method was…

计算机视觉与模式识别 · 计算机科学 2024-11-27 Jinpeng Liu , Jiale Xu , Weihao Cheng , Yiming Gao , Xintao Wang , Ying Shan , Yansong Tang

In this paper, we propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Existing neural radiance fields (NeRF) based solutions learn the deformation in an implicit manner, which cannot incorporate 3D…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Zhicheng Lu , Xiang Guo , Le Hui , Tianrui Chen , Min Yang , Xiao Tang , Feng Zhu , Yuchao Dai

While neural rendering has demonstrated impressive capabilities in 3D scene reconstruction and novel view synthesis, it heavily relies on high-quality sharp images and accurate camera poses. Numerous approaches have been proposed to train…

计算机视觉与模式识别 · 计算机科学 2024-03-20 Lingzhe Zhao , Peng Wang , Peidong Liu

Dynamic novel view synthesis (NVS) is essential for creating immersive experiences. Existing approaches have advanced dynamic NVS by introducing 3D Gaussian Splatting (3DGS) with implicit deformation fields or indiscriminately assigned…

计算机视觉与模式识别 · 计算机科学 2025-12-17 Kaizhe Zhang , Yijie Zhou , Weizhan Zhang , Caixia Yan , Haipeng Du , yugui xie , Yu-Hui Wen , Yong-Jin Liu

Feed-forward based 3D Gaussian Splatting methods have demonstrated exceptional capability in real-time novel view synthesis for human models. However, current approaches are confined to either dense viewpoint configurations or restricted…

计算机视觉与模式识别 · 计算机科学 2025-03-13 Yingdong Hu , Zhening Liu , Jiawei Shao , Zehong Lin , Jun Zhang

Novel View Synthesis (NVS) can reconstruct scenes from multi-view images and synthesize novel images from new viewpoints, which provides technical support for tasks such as target recognition and environmental perception. Aerial remote…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Yiling Yao , Bing Zhang , Wenjuan Zhang , Lianru Gao , Dailiang Peng , Bocheng Li , Yaning Wang , Bowen Wang

Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Minjun Kang , Inkyu Shin , Taeyeop Lee , Myungchul Kim , In So Kweon , Kuk-Jin Yoon

The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Tong Wu , Yu-Jie Yuan , Ling-Xiao Zhang , Jie Yang , Yan-Pei Cao , Ling-Qi Yan , Lin Gao