中文
相关论文

相关论文: MesonGS: Post-training Compression of 3D Gaussians…

200 篇论文

3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective…

计算机视觉与模式识别 · 计算机科学 2025-02-12 Yihang Chen , Qianyi Wu , Weiyao Lin , Mehrtash Harandi , Jianfei Cai

3D Gaussian Splatting (3D-GS) technique couples 3D Gaussian primitives with differentiable rasterization to achieve high-quality novel view synthesis results while providing advanced real-time rendering performance. However, due to the flaw…

计算机视觉与模式识别 · 计算机科学 2024-04-17 Zongxin Ye , Wenyu Li , Sidun Liu , Peng Qiao , Yong Dou

Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated remarkable capabilities in real-time and photorealistic novel view synthesis. However, traditional 3DGS representations often struggle with large-scale scene management and…

图形学 · 计算机科学 2025-08-08 Zijian Wang , Beizhen Zhao , Hao Wang

We present LocoGS, a locality-aware 3D Gaussian Splatting (3DGS) framework that exploits the spatial coherence of 3D Gaussians for compact modeling of volumetric scenes. To this end, we first analyze the local coherence of 3D Gaussian…

计算机视觉与模式识别 · 计算机科学 2025-03-13 Seungjoo Shin , Jaesik Park , Sunghyun Cho

3D Gaussian Splatting (GS) demonstrates excellent rendering quality and generation speed in novel view synthesis. However, substantial data size poses challenges for storage and transmission, making 3D GS compression an essential…

计算机视觉与模式识别 · 计算机科学 2025-03-18 He Huang , Wenjie Huang , Qi Yang , Yiling Xu , Zhu li

Recently, immersive media and autonomous driving applications have significantly advanced through 3D Gaussian Splatting (3DGS), which offers high-fidelity rendering and computational efficiency. Despite these advantages, 3DGS as a…

图形学 · 计算机科学 2025-05-27 Kangli Wang , Shihao Li , Qianxi Yi , Wei Gao

3D Gaussian Splatting enables high-quality real-time rendering but often produces millions of splats, resulting in excessive storage and computational overhead. We propose a novel lossy compression method based on learnable confidence…

图形学 · 计算机科学 2025-07-01 AmirHossein Naghi Razlighi , Elaheh Badali Golezani , Shohreh Kasaei

Recent advances in 3D Gaussian Splatting have allowed for real-time, high-fidelity novel view synthesis. Nonetheless, these models have significant storage requirements for large and medium-sized scenes, hindering their deployment over…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Diego Revilla , Pooja Suresh , Anand Bhojan , Ooi Wei Tsang

With the emergence of 3D Gaussian Splatting (3DGS), numerous pioneering efforts have been made to address the effective compression issue of massive 3DGS data. 3DGS offers an efficient and scalable representation of 3D scenes by utilizing…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Zhiye Tang , Lingzhuo Liu , Shengjie Jiao , Qiudan Zhang , Junhui Hou , You Yang , Xu Wang

The dominant 3D Gaussian splatting (3DGS) acceleration methods fail to properly regulate the number of Gaussians during training, causing redundant computational time overhead. In this paper, we propose FastGS, a novel, simple, and general…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Shiwei Ren , Tianci Wen , Yongchun Fang , Biao Lu

Recent advances in real-time neural rendering using point-based techniques have enabled broader adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting impose substantial storage overhead, as…

计算机视觉与模式识别 · 计算机科学 2024-11-13 Zhiwen Fan , Kevin Wang , Kairun Wen , Zehao Zhu , Dejia Xu , Zhangyang Wang

3D Gaussian Splatting (3DGS) has emerged as a high-fidelity and efficient paradigm for online free-viewpoint video (FVV) reconstruction, offering viewers rapid responsiveness and immersive experiences. However, existing online methods face…

计算机视觉与模式识别 · 计算机科学 2025-11-17 Jiacong Chen , Qingyu Mao , Youneng Bao , Xiandong Meng , Fanyang Meng , Ronggang Wang , Yongsheng Liang

We present a novel approach for enhancing the resolution and geometric fidelity of 3D Gaussian Splatting (3DGS) beyond native training resolution. Current 3DGS methods are fundamentally limited by their input resolution, producing…

图形学 · 计算机科学 2025-06-10 Shuja Khalid , Mohamed Ibrahim , Yang Liu

We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient splat-wise features to model 3D space which capture abstracted cues, including color, opacity,…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Haishan Wang , Mohammad Hassan Vali , Arno Solin

Neural scene representations, such as 3D Gaussian Splatting (3DGS), have enabled high-quality neural rendering; however, their large storage and transmission costs hinder deployment in resource-constrained environments. Existing compression…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Jiaqi Chen , Xinhao Ji , Yuanyuan Gao , Hao Li , Yuning Gong , Yifei Liu , Dan Xu , Zhihang Zhong , Dingwen Zhang , Xiao Sun

3D Gaussian Splatting (3DGS) has substantial potential for enabling photorealistic Free-Viewpoint Video (FVV) experiences. However, the vast number of Gaussians and their associated attributes poses significant challenges for storage and…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Qiang Hu , Zihan Zheng , Houqiang Zhong , Sihua Fu , Li Song , XiaoyunZhang , Guangtao Zhai , Yanfeng Wang

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

3D Gaussian splatting provides excellent visual quality for novel view synthesis, with fast training and real-time rendering; unfortunately, the memory requirements of this method for storing and transmission are unreasonably high. We first…

计算机视觉与模式识别 · 计算机科学 2024-06-26 Panagiotis Papantonakis , Georgios Kopanas , Bernhard Kerbl , Alexandre Lanvin , George Drettakis

3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis due to its efficient rendering capabilities. However, 3DGS demands relatively significant GPU memory, limiting its use on…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Hengyu Liu , Yuehao Wang , Chenxin Li , Ruisi Cai , Kevin Wang , Wuyang Li , Pavlo Molchanov , Peihao Wang , Zhangyang Wang

In recent times, the utilization of 3D models has gained traction, owing to the capacity for end-to-end training initially offered by Neural Radiance Fields and more recently by 3D Gaussian Splatting (3DGS) models. The latter holds a…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Muhammad Salman Ali , Maryam Qamar , Sung-Ho Bae , Enzo Tartaglione