NUST Institutions Library Catalogue

3D Gaussian Splatting (3DGS) has emerged as a breakthrough in explicit radiance
fields and computer graphics which has enabled precise scene representation, real
time rendering, and efficient novel view synthesis. This paper explores the evolution
of 3D rendering and recent advancements in 3DGS, with a particular focus on
different techniques for synthesizing novel views with the incorporation of deep
learning architectures especially transformers. To enhance scene quality, this
research investigates the integration of monocular depth information during
rendering and refines the loss function to improve reconstruction accuracy. By
incorporating depth information our method enhances geometric details by
capturing intricate details and reduction of artifacts. The findings contribute to the
reconstruction of 3D scene with high fidelity, offering insights to optimize Gaussian
Splatting technique for more efficient and realistic 3D rendering applications.