中文
相关论文

相关论文: Plug-and-Play PDE Optimization for 3D Gaussian Spl…

200 篇论文

Recent advancements in 3D Gaussian Splatting (3DGS) have greatly influenced neural fields, as it enables high-fidelity rendering with impressive visual quality. However, 3DGS has difficulty accurately representing surfaces. In contrast,…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Haofan Ren , Qingsong Yan , Ming Lu , Rongfeng Lu , Zunjie Zhu

In this paper, we aim ambitiously for a realistic yet challenging problem, namely, how to reconstruct high-quality 3D scenes from sparse low-resolution views that simultaneously suffer from deficient perspectives and clarity. Whereas…

计算机视觉与模式识别 · 计算机科学 2025-03-07 Yecong Wan , Mingwen Shao , Yuanshuo Cheng , Wangmeng Zuo

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

Recently, Gaussian Splatting (GS) has received a lot of attention in surface reconstruction. However, while 3D objects can be of complex and diverse shapes in the real world, existing GS-based methods only limitedly use a single type of…

计算机视觉与模式识别 · 计算机科学 2025-07-16 Haoxuan Qu , Yujun Cai , Hossein Rahmani , Ajay Kumar , Junsong Yuan , Jun Liu

While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction, it suffers from significant overhead due to massive redundant primitives. Existing compression methods typically rely on local sampling or fixed pruning thresholds,…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Beizhen Zhao , Sicheng Yu , Ziran Yin , Dongxu Shen , Hao Wang

Recent studies in Radiance Fields have paved the robust way for novel view synthesis with their photorealistic rendering quality. Nevertheless, they usually employ neural networks and volumetric rendering, which are costly to train and…

计算机视觉与模式识别 · 计算机科学 2024-09-25 Byeonghyeon Lee , Howoong Lee , Xiangyu Sun , Usman Ali , Eunbyung Park

While 3D Gaussian Splatting (3DGS) has revolutionized real-time photorealistic view synthesis, its fundamental reliance on symmetric Gaussian distributions introduces visual artifacts that hinder accurate spatial data exploration.…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Beizhen Zhao , Yifan Zhou , Gaochao Song , Ziran Yin , Hao Wang

3D Gaussian Splatting (3DGS) achieves remarkable results in the field of surface reconstruction. However, when Gaussian normal vectors are aligned within the single-view projection plane, while the geometry appears reasonable in the current…

计算机视觉与模式识别 · 计算机科学 2025-08-14 Bo Jia , Yanan Guo , Ying Chang , Benkui Zhang , Ying Xie , Kangning Du , Lin Cao

While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-view…

计算机视觉与模式识别 · 计算机科学 2026-05-01 Jian Lin , Jiancheng Fang , Shaoyu Wang , Changan Lai , Yikun Zhang , Yang Chen , Qiegen Liu

3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in scene synthesis and novel view synthesis tasks. Typically, the initialization of 3D Gaussian primitives relies on point clouds derived from Structure-from-Motion (SfM)…

计算机视觉与模式识别 · 计算机科学 2024-09-16 Shan Chen , Jiale Zhou , Lei Li

In this paper, we present a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting. Representing a 3D scene by combining numerous Gaussian splats has yielded outstanding visual quality. However, it…

计算机视觉与模式识别 · 计算机科学 2024-01-05 Jaeyoung Chung , Jeongtaek Oh , Kyoung Mu Lee

3D Gaussian Splatting (3DGS) is a powerful alternative to Neural Radiance Fields (NeRF), excelling in complex scene reconstruction and efficient rendering. However, it relies on high-quality point clouds from Structure-from-Motion (SfM),…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Ziao Liu , Zhenjia Li , Yifeng Shi , Xiangang Li

Novel view synthesis has advanced significantly with the development of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS). However, achieving high quality without compromising real-time rendering remains challenging,…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Zhongpai Gao , Benjamin Planche , Meng Zheng , Anwesa Choudhuri , Terrence Chen , Ziyan Wu

Dynamic extensions of 3D Gaussian Splatting (3DGS) achieve high-quality reconstructions through neural motion fields, but per-Gaussian neural inference makes these models computationally expensive. Building on DeformableGS, we introduce…

图形学 · 计算机科学 2026-03-31 Allen Tu , Haiyang Ying , Alex Hanson , Yonghan Lee , Tom Goldstein , Matthias Zwicker

Physical simulation predicts future states of objects based on material properties and external loads, enabling blueprints for both Industry and Engineering to conduct risk management. Current 3D reconstruction-based simulators typically…

机器学习 · 计算机科学 2026-02-20 Yicheng Cao , Zhuo Huang , Yu Yao , Yiming Ying , Daoyi Dong , Tongliang Liu

Dynamic scene reconstruction poses a persistent challenge in 3D vision. Deformable 3D Gaussian Splatting has emerged as an effective method for this task, offering real-time rendering and high visual fidelity. This approach decomposes a…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Bing He , Yunuo Chen , Guo Lu , Qi Wang , Qunshan Gu , Rong Xie , Li Song , Wenjun Zhang

Recently, the integration of the efficient feed-forward scheme into 3D Gaussian Splatting (3DGS) has been actively explored. However, most existing methods focus on sparse view reconstruction of small regions and cannot produce eligible…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Yunsong Wang , Tianxin Huang , Hanlin Chen , Gim Hee Lee

Reconstructing deformable endoscopic tissues is crucial for achieving robot-assisted surgery. However, 3D Gaussian Splatting-based approaches encounter challenges in achieving consistent tissue surface reconstruction, while existing…

计算机视觉与模式识别 · 计算机科学 2026-02-25 Yangsen Chen , Hao Wang

We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Hidenobu Matsuki , Riku Murai , Paul H. J. Kelly , Andrew J. Davison

3D Gaussian Splatting (3DGS) achieves an appealing balance between rendering quality and efficiency, but relies on approximating 3D Gaussians as 2D projections--an assumption that degrades accuracy, especially under generic large…

图形学 · 计算机科学 2026-03-13 Zixun Huang , Cho-Ying Wu , Yuliang Guo , Xinyu Huang , Liu Ren