01638nam a22001697a 4500082001000000100003200010245010100042264003800143300003100181500096900212650006301181700003901244856005701283942001301340999001901353952009601372  a629.8  aUllah Noor, Zabeeh 9129051  aENHANCED NOVEL VIEW SYTHESIS VIA DEEP LEARNING-BASED 3D GAUSSIAN SPLATTING /c Zabeeh Ullah Noor  aIslamabad: bSMME- NUST. c2024.   a83p. ;bSoft Copy, c30cm.  a3D 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.  aMS Robotics and Intelligent Machine Engineering   9119486  aSupervisor : Dr Sara Baber9129046  uhttp://10.250.8.41:8080/xmlui/handle/123456789/52946  2ddccTHE  c613800d613800  00104070aSMMEbSMMEcEBd2025-05-22l0o629.8pSMME-TH-1132r2025-05-22w2025-05-22yTHE