中文
相关论文

相关论文: E-3DGS: Event-Based Novel View Rendering of Large-…

200 篇论文

Over the past year, 3D Gaussian Splatting (3DGS) has received significant attention for its ability to represent 3D scenes in a perceptually accurate manner. However, it can require a substantial amount of storage since each splat's…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Brent Zoomers , Maarten Wijnants , Ivan Molenaers , Joni Vanherck , Jeroen Put , Lode Jorissen , Nick Michiels

We present BetterScene, an approach to enhance novel view synthesis (NVS) quality for diverse real-world scenes using extremely sparse, unconstrained photos. BetterScene leverages the production-ready Stable Video Diffusion (SVD) model…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Yuci Han , Charles Toth , John E. Anderson , William J. Shuart , Alper Yilmaz

Recent 3D novel view synthesis (NVS) methods often require extensive 3D data for training, and also typically lack generalization beyond the training distribution. Moreover, they tend to be object centric and struggle with complex and…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Taewon Kang , Divya Kothandaraman , Dinesh Manocha , Ming C. Lin

3D Gaussian Splatting (3DGS) has recently enabled real-time rendering of unbounded 3D scenes for novel view synthesis. However, this technique requires dense training views to accurately reconstruct 3D geometry. A limited number of input…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Haolin Xiong , Sairisheek Muttukuru , Rishi Upadhyay , Pradyumna Chari , Achuta Kadambi

High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with handheld cameras. We present a method that adapts to camera…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Otto Seiskari , Jerry Ylilammi , Valtteri Kaatrasalo , Pekka Rantalankila , Matias Turkulainen , Juho Kannala , Esa Rahtu , Arno Solin

Recently, 3D Gaussian Splatting (3DGS) has emerged as a powerful alternative to NeRF-based approaches, enabling real-time, high-quality novel view synthesis through explicit, optimizable 3D Gaussians. However, 3DGS suffers from significant…

计算机视觉与模式识别 · 计算机科学 2025-09-24 Zipeng Wang , Dan Xu

Reconstructing dynamic humans together with static scenes from monocular videos remains difficult, especially under fast motion, where RGB frames suffer from motion blur. Event cameras exhibit distinct advantages, e.g., microsecond temporal…

计算机视觉与模式识别 · 计算机科学 2025-09-24 Xiaoting Yin , Hao Shi , Kailun Yang , Jiajun Zhai , Shangwei Guo , Lin Wang , Kaiwei Wang

Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene…

计算机视觉与模式识别 · 计算机科学 2024-02-23 Zeyu Yang , Hongye Yang , Zijie Pan , Li Zhang

The recently developed Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown encouraging and impressive results for visual SLAM. However, most representative methods require RGBD sensors and are only available for indoor…

计算机视觉与模式识别 · 计算机科学 2025-05-16 Zhe Xin , Chenyang Wu , Penghui Huang , Yanyong Zhang , Yinian Mao , Guoquan Huang

Reconstructing a 3D scene from images is challenging due to the different ways light interacts with surfaces depending on the viewer's position and the surface's material. In classical computer graphics, materials can be classified as…

计算机视觉与模式识别 · 计算机科学 2025-02-03 Mateusz Nowak , Wojciech Jarosz , Peter Chin

3D Gaussian Splatting is a novel method for 3D view synthesis, which can gain an implicit neural learning rendering result than the traditional neural rendering technology but keep the more high-definition fast rendering speed. But it is…

计算机视觉与模式识别 · 计算机科学 2024-05-13 Jinwei Lin

The recent introduction of 3D Gaussian Splatting (3DGS) has significantly advanced novel view synthesis. Several studies have further improved the rendering quality of 3DGS, yet they still exhibit noticeable visual discrepancies when…

计算机视觉与模式识别 · 计算机科学 2025-11-20 Junseo Koo , Jinseo Jeong , Gunhee Kim

3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients to grow Gaussians to…

计算机视觉与模式识别 · 计算机科学 2024-12-09 Qingshan Xu , Jiequan Cui , Xuanyu Yi , Yuxuan Wang , Yuan Zhou , Yew-Soon Ong , Hanwang Zhang

Visualization of large-scale time-dependent simulation data is crucial for domain scientists to analyze complex phenomena, but it demands significant I/O bandwidth, storage, and computational resources. To enable effective visualization on…

图形学 · 计算机科学 2025-07-18 Siyuan Yao , Chaoli Wang

3D Gaussian Splatting (3DGS) techniques have achieved satisfactory 3D scene representation. Despite their impressive performance, they confront challenges due to the limitation of structure-from-motion (SfM) methods on acquiring accurate…

计算机视觉与模式识别 · 计算机科学 2025-01-28 Ao Gao , Luosong Guo , Tao Chen , Zhao Wang , Ying Tai , Jian Yang , Zhenyu Zhang

We introduce a method for novel view synthesis given only a single wide-baseline stereo image pair. In this challenging regime, 3D scene points are regularly observed only once, requiring prior-based reconstruction of scene geometry and…

计算机视觉与模式识别 · 计算机科学 2023-04-18 Yilun Du , Cameron Smith , Ayush Tewari , Vincent Sitzmann

This paper describes the Qualcomm AI Research solution to the RealADSim-NVS challenge, hosted at the RealADSim Workshop at ICCV 2025. The challenge concerns novel view synthesis in street scenes, and participants are required to generate,…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Mohamed Omran , Farhad Zanjani , Davide Abati , Jens Petersen , Amirhossein Habibian

Jointly estimating camera poses and mapping scenes from RGBD images is a fundamental task in simultaneous localization and mapping (SLAM). State-of-the-art methods employ 3D Gaussians to represent a scene, and render these Gaussians through…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Pengchong Hu , Zhizhong Han

The field of Novel View Synthesis has been revolutionized by 3D Gaussian Splatting (3DGS), which enables high-quality scene reconstruction that can be rendered in real-time. 3DGS-based techniques typically suffer from high GPU memory and…

图形学 · 计算机科学 2025-10-27 Umar Farooq , Jean-Yves Guillemaut , Adrian Hilton , Marco Volino

Gaussian splatting enables fast novel view synthesis in static 3D environments. However, reconstructing real-world environments remains challenging as distractors or occluders break the multi-view consistency assumption required for…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Yihao Wang , Marcus Klasson , Matias Turkulainen , Shuzhe Wang , Juho Kannala , Arno Solin