본문 바로가기
  • Home

Gaussian Blending: Improved 3D Gaussian Splatting for Model Light-Weighting and Deep Learning-Based Performance Enhancement

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2024, 29(8), pp.23-32
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : June 11, 2024
  • Accepted : July 24, 2024
  • Published : August 30, 2024

Yeong-In Lee 1 Jin-Nyeong Heo 1 Ji-Hwan Moon 1 Ha-Young Kim 1

1연세대학교

Accredited

ABSTRACT

NVS (Novel View Synthesis) is a field in computer vision that reconstructs new views of a scene from a set of input views. Real-time rendering and high performance are essential for NVS technology to be effectively utilized in various applications. Recently, 3D-GS (3D Gaussian Splatting) has gained popularity due to its faster training and inference times compared to those of NeRF (Neural Radiance Fields)-based methodologies. However, since 3D-GS reconstructs a 3D (Three-Dimensional) scene by splitting and cloning (Density Control) Gaussian points, the number of Gaussian points continuously increases, causing the model to become heavier as training progresses. To address this issue, we propose two methodologies: 1) Gaussian blending, an improved density control methodology that removes unnecessary Gaussian points, and 2) a performance enhancement methodology using a depth estimation model to minimize the loss in representation caused by the blending of Gaussian points. Experiments on the Tanks and Temples Dataset show that the proposed methodologies reduce the number of Gaussian points by up to 4% while maintaining performance.

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.