中文
相关论文

相关论文: Accelerating 3D Gaussian Splatting using Tensor Co…

200 篇论文

Recent years have witnessed the rapid emergence of 3D Gaussian splatting (3DGS) as a powerful approach for 3D reconstruction and novel view synthesis. Its explicit representation with Gaussian primitives enables fast training, real-time…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Haato Watanabe , Nobuyuki Umetani

3D Gaussian Splatting (3D-GS) has recently attracted great attention with real-time and photo-realistic renderings. This technique typically takes perspective images as input and optimizes a set of 3D elliptical Gaussians by splatting them…

计算机视觉与模式识别 · 计算机科学 2024-02-02 Jiayang Bai , Letian Huang , Jie Guo , Wen Gong , Yuanqi Li , Yanwen Guo

Particle-based representations of radiance fields such as 3D Gaussian Splatting have found great success for reconstructing and re-rendering of complex scenes. Most existing methods render particles via rasterization, projecting them to…

3D Gaussian Splatting (3DGS) has shown promising performance in novel view synthesis. Previous methods adapt it to obtaining surfaces of either individual 3D objects or within limited scenes. In this paper, we make the first attempt to…

计算机视觉与模式识别 · 计算机科学 2024-09-11 Junyi Chen , Weicai Ye , Yifan Wang , Danpeng Chen , Di Huang , Wanli Ouyang , Guofeng Zhang , Yu Qiao , Tong He

Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable success in producing photorealistic renderings with efficient…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Xi Liu , Chaoyi Zhou , Siyu Huang

Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerged as an appealing…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Seungjun Oh , Younggeun Lee , Hyejin Jeon , Eunbyung Park

We introduce an image upscaling technique tailored for 3D Gaussian Splatting (3DGS) on lightweight GPUs. Compared to 3DGS, it achieves significantly higher rendering speeds and reduces artifacts commonly observed in 3DGS reconstructions.…

计算机视觉与模式识别 · 计算机科学 2025-09-18 Simon Niedermayr , Christoph Neuhauser Rüdiger Westermann

Reconstructing transparent surfaces is essential for tasks such as robotic manipulation in labs, yet it poses a significant challenge for 3D reconstruction techniques like 3D Gaussian Splatting (3DGS). These methods often encounter a…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Mingwei Li , Pu Pang , Hehe Fan , Hua Huang , Yi Yang

The advent of 3D Gaussian Splatting has revolutionized graphics rendering by delivering high visual quality and fast rendering speeds. However, training large-scale scenes at high quality remains challenging due to the substantial memory…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Donghyun Lee , Dawoon Jeong , Jae W. Lee , Hongil Yoon

3D Gaussian Splatting (3DGS) has emerged as a key rendering pipeline for digital asset creation due to its balance between efficiency and visual quality. To address the issues of unstable pose estimation and scene representation distortion…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Meijun Guo , Yongliang Shi , Caiyun Liu , Yixiao Feng , Ming Ma , Tinghai Yan , Weining Lu , Bin Liang

3D Gaussian Splatting (3DGS) achieves impressive rendering fidelity and speed for novel view synthesis. However, its substantial data size poses a significant challenge for practical applications. While many compression techniques have been…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Yihang Chen , Mengyao Li , Qianyi Wu , Weiyao Lin , Mehrtash Harandi , Jianfei Cai

3D Gaussian Splatting (3DGS) has recently emerged as a promising 3D representation. Much research has been focused on reducing its storage requirements and memory footprint. However, the needs to compress and transmit the 3DGS…

计算机视觉与模式识别 · 计算机科学 2025-03-10 Yu-Ting Zhan , Cheng-Yuan Ho , Hebi Yang , Yi-Hsin Chen , Jui Chiu Chiang , Yu-Lun Liu , Wen-Hsiao Peng

In this paper, we propose UniGS, a unified map representation and differentiable framework for high-fidelity multimodal 3D reconstruction based on 3D Gaussian Splatting. Our framework integrates a CUDA-accelerated rasterization pipeline…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Yusen Xie , Zhenmin Huang , Jianhao Jiao , Dimitrios Kanoulas , Jun Ma

The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations. While demonstrating the potential for real-time rendering, 3D-GS encounters rendering…

计算机视觉与模式识别 · 计算机科学 2024-10-18 Kerui Ren , Lihan Jiang , Tao Lu , Mulin Yu , Linning Xu , Zhangkai Ni , Bo Dai

Recent advances in novel view synthesis have enabled real-time rendering speeds with high reconstruction accuracy. 3D Gaussian Splatting (3D-GS), a foundational point-based parametric 3D scene representation, models scenes as large sets of…

计算机视觉与模式识别 · 计算机科学 2025-11-21 Alex Hanson , Allen Tu , Vasu Singla , Mayuka Jayawardhana , Matthias Zwicker , Tom Goldstein

3D Gaussian Splatting (3DGS) is a state-of-art technique to model real-world scenes with high quality and real-time rendering. Typically, a higher quality representation can be achieved by using a large number of 3D Gaussians. However,…

NeRF-based 3D-aware Generative Adversarial Networks (GANs) like EG3D or GIRAFFE have shown very high rendering quality under large representational variety. However, rendering with Neural Radiance Fields poses challenges for 3D…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Florian Barthel , Arian Beckmann , Wieland Morgenstern , Anna Hilsmann , Peter Eisert

Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited. However, existing rendering-based self-supervised frameworks are…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Hao Liu , Minglin Chen , Yanni Ma , Haihong Xiao , Ying He

Novel view synthesis (NVS) and surface reconstruction (SR) are essential tasks in 3D Gaussian Splatting (3D-GS). Despite recent progress, these tasks are often addressed independently, with GS-based rendering methods struggling under…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Qingyuan Zhou , Yuehu Gong , Weidong Yang , Jiaze Li , Yeqi Luo , Baixin Xu , Shuhao Li , Ben Fei , Ying He

3D Gaussian Splatting (3DGS) is a highly deployable real-time method for novel view synthesis. In practice, it requires a universal, consistent control mechanism that adjusts the trade-off between rendering quality and model compression…

计算机视觉与模式识别 · 计算机科学 2025-11-10 Fengdi Zhang , Yibao Sun , Hongkun Cao , Ruqi Huang