logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

QuantizationGS: Differentiable quantization model for 3D Gaussian Splatting compression

delete2026-04-17
delete0
PRE
AI
Y
Yiming Ma
H
Hanlin Mou
J
Jing Tian
T
Tong Liu *
D
Daobing Zhang *
DOI：10.1016/j.cag.2026.104596delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
• 通过在训练过程中向参数注入量化噪声来压缩模型。 • 使用全局重要性评分机制修剪冗余锚点以提高渲染速度。 • 通过专用损失约束模型训练来保持重建质量。
Keyword:
Quantization
Gaussian Splatting
Model Compression
Anchor Point Pruning
Loss Constraining

期刊

C
computers & graphics
IF:
0
论文数:
119
被引数:
0

机构

C
China Academy of Information and Communications Technology
学者数:
69
论文数: 49
被引数: 0
C
Chinese Academy of Sciences
学者数:
3.9W
论文数: 1.5W
被引数: 58.4W
引用论文

引用论文

Pulsar: Efficient Sphere-based Neural Rendering
err2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2021-06-01
err0
errOAAI
errChristoph Lassner; Michael Zollhofer
err分享
err收藏
Compressing Volumetric Radiance Fields to 1 MB将体素辐射场压缩至1 MB
err2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2023-06-01
err0
errOAAI
errLingzhi Li; Zhen Shen; Zhongshu Wang; Li Shen; Liefeng Bo
err分享
err收藏
Strivec: Sparse Tri-Vector Radiance Fields
err2023 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2023-10-01
err0
PREAI
errGao,Quankai; Xu,Qiangeng; Su,Hao; Neumann,Ulrich; Xu,Zexiang
err分享
err收藏
Tanks and Temples: Benchmarking Large-Scale Scene Reconstruction坦克和寺庙: 大规模场景重建的基准
errACM TRANSACTIONS ON GRAPHICS
IF9.5
err2017-07-20
err636
PREAI
errKnapitsch, Arno; Park, Jaesik; Zhou, Qian-Yi; Koltun, Vladlen
err分享
err收藏
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene RepresentationNeRFCodec：神经特征压缩与神经辐射场相结合，实现内存高效的场景表示
err2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2024-06-16
err0
PREAI
errSicheng Li; Hao Li; Yiyi Liao; Lu Yu
err分享
err收藏
How Far can we Compress Instant-NGP-Based NeRF?基于Instant-NGP的NeRF可以压缩到什么程度？
err2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2024-06-16
err0
PREAI
errYihang Chen; Qianyi Wu; Mehrtash Harandi; Jianfei Cai
err分享
err收藏
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
err2021 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2021-10-01
err0
errOAAI
errJonathan T. Barron; Ben Mildenhall; Matthew Tancik; Peter Hedman; Ricardo Martin-Brualla; Pratul P. Srinivasan
err分享
err收藏
Masked Wavelet Representation for Compact Neural Radiance Fields掩蔽小波表示用于紧凑型神经辐射场
err2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2023-06-01
err0
errOAAI
errDaniel Rho; Byeonghyeon Lee; Seungtae Nam; Joo Chan Lee; Jong Hwan Ko; Eunbyung Park
err分享
err收藏
Statistical theory of quantization
errIEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
IF5.9
err1996-04-01
err382
PREAI
errWidrow, B; Kollar, I; Liu, MC
err分享
err收藏
Deep Blending for Free-Viewpoint Image-Based Rendering基于自由视点图像渲染的深度混合
errACM TRANSACTIONS ON GRAPHICS
IF9.5
err2018-12-04
err26
errOAAI
errHedman, Peter; Philip, Julien; Price, True; Frahm, Jan-Michael; Drettakis, George; Brostow, Gabriel
err分享
err收藏
学者 查看更多内容