中文
相关论文

相关论文: UHD-GPGNet: UHD Video Denoising via Gaussian-Proce…

200 篇论文

Current methods for restoring underexposed images typically rely on supervised learning with paired underexposed and well-illuminated images. However, collecting such datasets is often impractical in real-world scenarios. Moreover, these…

计算机视觉与模式识别 · 计算机科学 2025-07-04 Hailong Yan , Junjian Huang , Tingwen Huang

Real-time immersive video communications, particularly high-fidelity 3D telepresence, necessitates a synergistic balance between instantaneous dynamic scene reconstruction and high-efficiency data transmission. While recent advancements in…

图像与视频处理 · 电气工程与系统科学 2026-04-29 Dingxi Yang , Wenqi Guo , Yue Liu , Jungong Han , Zhijin Qin

Spatially varying image deblurring remains a fundamentally ill-posed problem, especially when degradations arise from complex mixtures of motion and other forms of blur under significant noise. State-of-the-art learning-based approaches…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Hakki Motorcu , Mujdat Cetin

Recent research on the robustness of Graph Neural Networks (GNNs) under noises or attacks has attracted great attention due to its importance in real-world applications. Most previous methods explore a single noise source, recovering…

机器学习 · 计算机科学 2024-08-02 Tianmeng Yang , Jiahao Meng , Min Zhou , Yaming Yang , Yujing Wang , Xiangtai Li , Yunhai Tong

Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric…

图形学 · 计算机科学 2025-07-21 Zinuo You , Stamatios Georgoulis , Anpei Chen , Siyu Tang , Dengxin Dai

We present Inst4DGS, an instance-decomposed 4D Gaussian Splatting (4DGS) approach with long-horizon per-Gaussian trajectories. While dynamic 4DGS has advanced rapidly, instance-decomposed 4DGS remains underexplored, largely due to the…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Yonghan Lee , Dinesh Manocha

Effective and efficient tokenization plays an important role in image representation and generation. Conventional methods, constrained by uniform 2D/1D grid tokenization, are inflexible to represent regions with varying shapes and textures…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Zhengqiang Zhang , Rongyuan Wu , Lingchen Sun , Lei Zhang

Background subtraction (BGS) is a fundamental video processing task which is a key component of many applications. Deep learning-based supervised algorithms achieve very good perforamnce in BGS, however, most of these algorithms are…

计算机视觉与模式识别 · 计算机科学 2021-02-26 M. Ozan Tezcan , Prakash Ishwar , Janusz Konrad

Existing denoising methods typically restore clear results by aggregating pixels from the noisy input. Instead of relying on hand-crafted aggregation schemes, we propose to explicitly learn this process with deep neural networks. We present…

计算机视觉与模式识别 · 计算机科学 2021-02-03 Xiangyu Xu , Muchen Li , Wenxiu Sun , Ming-Hsuan Yang

High-fidelity rendering of dynamic humans from monocular videos typically degrades catastrophically under occlusions. Existing solutions incorporate external priors-either hallucinating missing content via generative models, which induces…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Weiquan Wang , Feifei Shao , Lin Li , Zhen Wang , Jun Xiao , Long Chen

We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Zhen Xu , Zhengqin Li , Zhao Dong , Xiaowei Zhou , Richard Newcombe , Zhaoyang Lv

Ultrasound imaging is a cornerstone of non-invasive clinical diagnostics, yet its limited field of view poses challenges for novel view synthesis. We present UltraGS, a real-time framework that adapts Gaussian Splatting to sensorless…

计算机视觉与模式识别 · 计算机科学 2026-04-29 Yuezhe Yang , Qingqing Ruan , Wenjie Cai , Yudang Dong , Dexin Yang , Xingbo Dong , Zhe Jin , Yong Dai

Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance significantly degrades in dynamic environments. This…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Ying Zang , Xuanyi Liu , Yidong Han , Deyi Ji , Chaotao Ding , Yuanqi Hu , Qi Zhu , Xuanfu Li , Jin Ma , Lingyun Sun , Tianrun Chen , Lanyun Zhu

Reconstructing dynamic 3D scenes from monocular video has broad applications in AR/VR, robotics, and autonomous navigation, but often fails due to severe motion blur caused by camera and object motion. Existing methods commonly follow a…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Zhijing Wu , Longguang Wang

In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture. Until recently, video denoising with neural networks had been a largely under explored domain, and existing methods…

计算机视觉与模式识别 · 计算机科学 2020-05-01 Matias Tassano , Julie Delon , Thomas Veit

Intrinsic image decomposition aims to estimate physically based rendering (PBR) parameters such as albedo, roughness, and metallicity from images. While recent methods achieve strong single-view predictions, applying them independently to…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Alara Dirik , Stefanos Zafeiriou

In this work, we introduce UniGS, a novel 3D Gaussian reconstruction and novel view synthesis model that predicts a high-fidelity representation of 3D Gaussians from arbitrary number of posed sparse-view images. Previous methods often…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Jiamin Wu , Kenkun Liu , Yukai Shi , Xiaoke Jiang , Yuan Yao , Lei Zhang

In real-world underwater environment, exploration of seabed resources, underwater archaeology, and underwater fishing rely on a variety of sensors, vision sensor is the most important one due to its high information content, non-intrusive,…

图像与视频处理 · 电气工程与系统科学 2021-03-29 Nan Wang , Yabin Zhou , Fenglei Han , Haitao Zhu , Jingzheng Yao

Reconstructing realistic underwater scenes from underwater video remains a meaningful yet challenging task in the multimedia domain. The inherent spatiotemporal degradations in underwater imaging, including caustics, flickering,…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Shaohua Liu , Ning Gao , Zuoya Gu , Hongkun Dou , Yue Deng , Hongjue Li

3D Gaussian Splatting (3DGS) represents a significant advancement in the field of efficient and high-fidelity novel view synthesis. Despite recent progress, achieving accurate geometric reconstruction under sparse-view conditions remains a…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Zexu Huang , Min Xu , Stuart Perry