MrNeRF (@janusch_patas)
2025-08-14 | โค๏ธ 107 | ๐ 14
A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
Contributions: This survey provides a comprehensive and structured review of recent literature on 3DGS, focusing on its emerging downstream applications.
We begin by introducing 2D foundation models that enable semantic control and understanding in 3DGS-based systems and briefly revisit relevant NeRF-based methods to establish conceptual continuity.
The core of our survey is organized around three major task categories: segmentation, editing, and generation. Within each category, we systematically compare representative works in terms of technical designs, learning paradigms, and supervision strategies.
We further analyze benchmark settings and performance results in each domain, aiming to provide a self-contained and accessible resource for both newcomers and experienced researchers.
Finally, we discuss open challenges and future research opportunities, with the goal of fostering deeper exploration and broader adoption of 3DGS across high-level vision and graphics application tasks.
๋ฏธ๋์ด
