paper-with-me

홈 › Papers

GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting

2024-11-09 · CVPR 2025 1 · Yangming Zhang, Wenqi Jia, Wei Niu, Miao Yin

3D Gaussian Splatting (3DGS) has emerged as a mainstream for novel view synthesis, leveraging continuous aggregations of Gaussian functions to model scene geometry. However, 3DGS suffers from substantial memory requirements to store the multitude of Gaussians, hindering its practicality. To address this challenge, we introduce GaussianSpa, an optimization-based simplification framework for compact and high-quality 3DGS. Specifically, we formulate the simplification as an optimization problem associated with the 3DGS training. Correspondingly, we propose an efficient "optimizing-sparsifying" solution that alternately solves two independent sub-problems, gradually imposing strong sparsity onto the Gaussians in the training process. Our comprehensive evaluations on various datasets show the superiority of GaussianSpa over existing state-of-the-art approaches. Notably, GaussianSpa achieves an average PSNR improvement of 0.9 dB on the real-world Deep Blending dataset with 10$\times$ fewer Gaussians compared to the vanilla 3DGS. Our project page is available at https://noodle-lab.github.io/gaussianspa/.

📄 PDF Abstract BibTeX arXiv:2411.06019

Code (0)

등록된 구현이 없습니다.

Tasks

3DGSNovel View Synthesis

Similar Papers 제목 키워드 기반

Privacy-Preserving Image Sharing via Sparsifying Layers on Convolutional Groups

2020-02-04 · Sohrab Ferdowsi, Behrooz Razeghi, Taras Holotyak, Flavio P. Calmon 외

We propose a practical framework to address the problem of privacy-aware image sharing in large-scale setups. We argue that, while compactness is always desired at scale, this need is more severe when trying to furthermo…

Privacy Preserving

Online Learning Sensing Matrix and Sparsifying Dictionary Simultaneously for Compressive Sensing

2017-01-04 · Tao Hong, Zhihui Zhu

This paper considers the problem of simultaneously learning the Sensing Matrix and Sparsifying Dictionary (SMSD) on a large training dataset. To address the formulated joint learning problem, we propose an online algorit…

Compressive Sensing

GaussianPOP: Principled Simplification Framework for Compact 3D Gaussian Splatting via Error Quantification

2026-02-06 · Soonbin Lee, Yeong-Gyu Kim, Simon Sasse, Tomas M. Borges 외 arxiv

Existing 3D Gaussian Splatting simplification methods commonly use importance scores, such as blending weights or sensitivity, to identify redundant Gaussians. However, these scores are not driven by visual error metrics…

Optimizing Statistical Machine Translation for Text Simplification

2016-01-01 · TACL 2016 1 · Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen 외

Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus. These methods are limited by the quality and quantit…

Machine TranslationSentenceText SimplificationTranslation

Learning Filter Bank Sparsifying Transforms

2018-03-06 · Luke Pfister, Yoram Bresler

Data is said to follow the transform (or analysis) sparsity model if it becomes sparse when acted on by a linear operator called a sparsifying transform. Several algorithms have been designed to learn such a transform di…

DenoisingImage Denoising