StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering

被引:3
|
作者
Radl, Lukas [1 ]
Steiner, Michael [1 ]
Parger, Mathias [1 ,2 ]
Weinrauch, Alexander
Kerbl, Bernhard [3 ]
Steinberger, Markus [1 ,2 ]
机构
[1] Graz Univ Technol, Graz, Austria
[2] Huawei Technol, Vienna, Austria
[3] TU Wien, Vienna, Austria
来源
ACM TRANSACTIONS ON GRAPHICS | 2024年 / 43卷 / 04期
关键词
Parallel Computing; Point-based Rendering; Real-Time Rendering;
D O I
10.1145/3658187
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Gaussian Splatting has emerged as a prominent model for constructing 3D representations from images across diverse domains. However, the efficiency of the 3D Gaussian Splatting rendering pipeline relies on several simplifications. Notably, reducing Gaussian to 2D splats with a single view-space depth introduces popping and blending artifacts during view rotation. Addressing this issue requires accurate per-pixel depth computation, yet a full per-pixel sort proves excessively costly compared to a global sort operation. In this paper, we present a novel hierarchical rasterization approach that systematically resorts and culls splats with minimal processing overhead. Our software rasterizer effectively eliminates popping artifacts and view inconsistencies, as demonstrated through both quantitative and qualitative measurements. Simultaneously, our method mitigates the potential for cheating view-dependent effects with popping, ensuring a more authentic representation. Despite the elimination of cheating, our approach achieves comparable quantitative results for test images, while increasing the consistency for novel view synthesis in motion. Due to its design, our hierarchical approach is only 4% slower on average than the original Gaussian Splatting. Notably, enforcing consistency enables a reduction in the number of Gaussians by approximately half with nearly identical quality and view-consistency. Consequently, rendering performance is nearly doubled, making our approach 1.6x faster than the original Gaussian Splatting, with a 50% reduction in memory requirements. Our renderer is publicly available at https://github.com/r4dl/StopThePop.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] View-Consistent 3D Editing with Gaussian Splatting
    Wang, Yuxuan
    Yi, Xuanyu
    Wu, Zike
    Zhao, Na
    Chen, Long
    Zhang, Hanwang
    COMPUTER VISION-ECCV 2024, PT XXXV, 2025, 15093 : 404 - 420
  • [2] 3D Gaussian Splatting for Real-Time Radiance Field Rendering
    Kerbl, Bernhard
    Kopanas, Georgios
    Leimkuehler, Thomas
    Drettakis, George
    ACM TRANSACTIONS ON GRAPHICS, 2023, 42 (04):
  • [3] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
    Wu, Guanjun
    Yi, Taoran
    Fang, Jiemin
    Xie, Lingxi
    Zhang, Xiaopeng
    Wei, Wei
    Liu, Wenyu
    Tian, Qi
    Wang, Xinggang
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, : 20310 - 20320
  • [4] VersatileGaussian: Real-Time Neural Rendering for Versatile Tasks Using Gaussian Splatting
    Li, Renjie
    Fang, Zhiwen
    Wang, Bohua
    Wang, Peihao
    Wang, Zhangyang
    Wu, Xi
    COMPUTER VISION - ECCV 2024, PT XX, 2025, 15078 : 258 - 275
  • [5] VC-GS: view-consistent deblurring Gaussian splatting via alternating branch optimization
    Cao, Qida
    Ding, Jiajun
    Liu, Zhenyang
    Kuang, Zhenzhong
    Shao, Yijie
    Shen, Yilan
    VISUAL COMPUTER, 2025,
  • [6] Frequency-importance gaussian splatting for real-time lightweight radiance field rendering
    Chen, Lizhe
    Hu, Yan
    Zhang, Yu
    Ge, Yuyao
    Zhang, Haoyu
    Cai, Xingquan
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (35) : 83377 - 83401
  • [7] Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting
    Ye, Sheng
    Dong, Zhen-Hui
    Hu, Yubin
    Wen, Yu-Hui
    Liu, Yong-Jin
    COMPUTER GRAPHICS FORUM, 2024, 43 (07)
  • [8] EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting
    Li, Chenxin
    Feng, Brandon Y.
    Liu, Yifan
    Liu, Hengyu
    Wang, Cheng
    Yu, Weihao
    Yuan, Yixuan
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2024, PT VI, 2024, 15006 : 252 - 262
  • [9] FSGS: Real-Time Few-Shot View Synthesis Using Gaussian Splatting
    Zhu, Zehao
    Fan, Zhiwen
    Jiang, Yifan
    Wan, Zhangyang
    COMPUTER VISION - ECCV 2024, PT XXXIX, 2025, 15097 : 145 - 163
  • [10] Real-time Large-scale Deformation of Gaussian Splatting
    Gao, Lin
    Yang, Jie
    Zhang, Bo-tao
    Sun, Jia-mu
    Yuan, Yu-jie
    Fu, Hongbo
    Lai, Yu-kun
    ACM TRANSACTIONS ON GRAPHICS, 2024, 43 (06):