While 3DGS (3D Gaussian Splatting) has recently emerged as a powerful approach for real-time novel view synthesis, its storage and computational demands remain significant. This PhD project focuses on compressive radiance fields, and more specifically 3DGS for efficient scene representation and rendering. The aim of the project is to explore compressive strategies to reduce memory footprint and improve scalability, while maintaining high visual fidelity.
PhD student: Jiarong Gong, LiU