中文
相关论文

相关论文: Splat-SAP: Feed-Forward Gaussian Splatting for Hum…

200 篇论文

Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a practical and scalable reconstruction method,…

计算机视觉与模式识别 · 计算机科学 2024-09-18 Marko Mihajlovic , Sergey Prokudin , Siyu Tang , Robert Maier , Federica Bogo , Tony Tung , Edmond Boyer

We consider the problem of novel view synthesis from unposed images in a single feed-forward. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS, where we further…

计算机视觉与模式识别 · 计算机科学 2025-07-25 Sunghwan Hong , Jaewoo Jung , Heeseong Shin , Jisang Han , Jiaolong Yang , Chong Luo , Seungryong Kim

Achieving real-time Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian splatting (3DGS) in large-scale real-world environments remains challenging, as existing methods still struggle to jointly achieve low-latency pose…

Reconstructing high-fidelity animatable human avatars from monocular videos remains challenging due to insufficient geometric information in single-view observations. While recent 3D Gaussian Splatting methods have shown promise, they…

计算机视觉与模式识别 · 计算机科学 2025-09-19 Jinlong Fan , Bingyu Hu , Xingguang Li , Yuxiang Yang , Jing Zhang

3D Shape represented as point cloud has achieve advancements in multimodal pre-training to align image and language descriptions, which is curial to object identification, classification, and retrieval. However, the discrete representations…

计算机视觉与模式识别 · 计算机科学 2024-02-14 Haoyuan Li , Yanpeng Zhou , Yihan Zeng , Hang Xu , Xiaodan Liang

Gaussian Splatting has changed the game for real-time photo-realistic rendering. One of the most popular applications of Gaussian Splatting is to create animatable avatars, known as Gaussian Avatars. Recent works have pushed the boundaries…

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To address…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Prajwal Gupta C. R. , Divyam Sheth , Jinjoo Ha , Mirela Ostrek , Justus Thies

Gaussian splatting has emerged as a competitive explicit representation for image and video reconstruction. In this work, we present P-GSVC, the first layered progressive 2D Gaussian splatting framework that provides a unified solution for…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Longan Wang , Yuang Shi , Wei Tsang Ooi

We introduce MVSplat360, a feed-forward approach for 360{\deg} novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and…

计算机视觉与模式识别 · 计算机科学 2024-11-08 Yuedong Chen , Chuanxia Zheng , Haofei Xu , Bohan Zhuang , Andrea Vedaldi , Tat-Jen Cham , Jianfei Cai

Reconstructing urban street scenes is crucial due to its vital role in applications such as autonomous driving and urban planning. These scenes are characterized by long and narrow camera trajectories, occlusion, complex object…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Xiao Cui , Weicai Ye , Yifan Wang , Guofeng Zhang , Wengang Zhou , Houqiang Li

Sparse-view scene reconstruction often faces significant challenges due to the constraints imposed by limited observational data. These limitations result in incomplete information, leading to suboptimal reconstructions using existing…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Xiangyu Sun , Runnan Chen , Mingming Gong , Dong Xu , Tongliang Liu

We introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we build a cost volume representation via plane sweeping, where…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Yuedong Chen , Haofei Xu , Chuanxia Zheng , Bohan Zhuang , Marc Pollefeys , Andreas Geiger , Tat-Jen Cham , Jianfei Cai

3D Gaussian Splatting (3DGS) has attracted great attention in novel view synthesis because of its superior rendering efficiency and high fidelity. However, the trained Gaussians suffer from severe zooming degradation due to non-adjustable…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Jiameng Li , Yue Shi , Jiezhang Cao , Bingbing Ni , Wenjun Zhang , Kai Zhang , Luc Van Gool

Achieving high-fidelity 3D reconstruction from monocular video remains challenging due to the inherent limitations of traditional methods like Structure-from-Motion (SfM) and monocular SLAM in accurately capturing scene details. While…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Yue Hu , Rong Liu , Meida Chen , Peter Beerel , Andrew Feng

Recent advancements in 3D Gaussian Splatting (3DGS) have demonstrated its potential for efficient and photorealistic 3D reconstructions, which is crucial for diverse applications such as robotics and immersive media. However, current…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Daheng Yin , Isaac Ding , Yili Jin , Jianxin Shi , Jiangchuan Liu

Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction,…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Yedong Shen , Shiqi Zhang , Sha Zhang , Yifan Duan , Xinran Zhang , Wenhao Yu , Lu Zhang , Jiajun Deng , Yanyong Zhang

Despite significant advancements in dynamic neural rendering, existing methods fail to address the unique challenges posed by UAV-captured scenarios, particularly those involving monocular camera setups, top-down perspective, and multiple…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Jaehoon Choi , Dongki Jung , Christopher Maxey , Yonghan Lee , Sungmin Eum , Dinesh Manocha , Heesung Kwon

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis with high visual quality. However, existing methods struggle with semi-transparent specular surfaces that exhibit both complex reflections and clear transmission, often…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Ji Shi , Xianghua Ying , Bowei Xing , Ruohao Guo , Wenzhen Yue

Novel view synthesis has been greatly enhanced by the development of radiance field methods. The introduction of 3D Gaussian Splatting (3DGS) has effectively addressed key challenges, such as long training times and slow rendering speeds,…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Gopi Raju Matta , Reddypalli Trisha , Kaushik Mitra

This paper presents Planar Gaussian Splatting (PGS), a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene, directly from multiple RGB images. The PGS leverages Gaussian primitives to model the scene…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Farhad G. Zanjani , Hong Cai , Hanno Ackermann , Leila Mirvakhabova , Fatih Porikli
‹ 上一页 1 8 9 10 下一页 ›