cs.CVNov 13, 2026

Stage-wise Lineage-aware Dropout for Sparse-View 3D Gaussian Splatting

Authors: Yan Xing, Zhi Chen, Fanglue Zhang, Junhong Zhao, Bing Xue, Mengjie Zhang

Organizations: School of Mathematics, Hefei University of Technology, Hefei 230009, China · School of Engineering and Computer Science, Victoria University of Wellington, Wellington 6140, New Zealand · Joint International Research Laboratory of Spatio-temporal Information and Intelligent Location Services, Guilin 541004, China · School of Computer Science and Engineering, University of New South Wales, Sydney 2052, Australia

Abstract

Sparse-view 3D Gaussian Splatting (3DGS) is prone to overfitting because only a limited number of images are available to constrain scene geometry. Dropout is one regularization strategy for alleviating this problem. We introduce the concept of a lineage family to describe a set of Gaussian primitives derived from the same founder through cloning or splitting operations. The founder Gaussians refer to all Gaussian primitives generated during initialization. Descendants within the same family often jointly contribute to the refinement of adjacent local regions. However, dropping individual Gaussians can be less effective due to the compensation effect from neighboring Gaussians for the dropped ones. To address this issue, we propose Stage-wise Lineage-aware Dropout(SLD), which applies lineage-family dropout during the structural regularization stage and switches to individual dropout during the later refinement stage. We further propose Lineage-Balanced Densification(LBD), which operates during densification by constructing an expanded candidate pool and reallocating the densification budget according to the mean gradient scores and existing descendant sizes of different families. Experiments on the LLFF, MipNeRF360, and Blender datasets show that the proposed framework achieves competitive performance in sparse-view reconstruction

Figures & tables

Explore similar work

CardsList
  1. PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting

    May 12, 2026Hantang Li, Qiang Zhu, Xiandong Meng +33D Gaussian SplattingSparse-View 3D Reconstruction

  2. Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting

    Feb 24, 2026Shuangkang Fang, I-Chao Shen, Xuanyang Zhang +53D Gaussian SplattingSparse-View 3D Reconstruction

  3. D3GS: Depth, DINO, and RGB Diffusion Co-Guided 3D Gaussian Splatting for Sparse-View Reconstruction

    Sep 19, 2026Yunqi Gao, Zhanfeng Liao, Hanzhang Tu +7Sparse-View 3D Reconstruction3D Gaussian Splatting