Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Real-Time Rendering for AR/VR with Novel View Synthesis

Maithani, Garima LU (2025) MAMM15 20251
Ergonomics and Aerosol Technology
Department of Design Sciences
Abstract
Real-time 3D reconstruction is crucial for immersive AR/VR but is hard to achieve with traditional photogrammetry and mesh-based pipelines due to latency and limited scalability. Neural Radiance Fields (NeRF) enable high-quality novel view synthesis but suffer from long training and slow rendering, while Gaussian Splatting (GS) achieves real-time rendering at the cost of heavy preprocessing and memory usage. This thesis presents a comparative study of NeRF and GS in terms of visual quality, efficiency, and scalability, and proposes an optimized GS-based pipeline for real-time AR/VR. The system introduces three main techniques: (1) clustering-based reduction of COLMAP points to cut preprocessing to under two minutes; (2) gradient-aware... (More)
Real-time 3D reconstruction is crucial for immersive AR/VR but is hard to achieve with traditional photogrammetry and mesh-based pipelines due to latency and limited scalability. Neural Radiance Fields (NeRF) enable high-quality novel view synthesis but suffer from long training and slow rendering, while Gaussian Splatting (GS) achieves real-time rendering at the cost of heavy preprocessing and memory usage. This thesis presents a comparative study of NeRF and GS in terms of visual quality, efficiency, and scalability, and proposes an optimized GS-based pipeline for real-time AR/VR. The system introduces three main techniques: (1) clustering-based reduction of COLMAP points to cut preprocessing to under two minutes; (2) gradient-aware clustering of Spherical Harmonic coefficients to shrink storage; and (3) quantization-aware training to reduce precision and memory requirements without harming visual quality. The optimized pipeline lowers total processing time to as little as 5 minutes, reaches up to 180 FPS at 1080p, reduces model size by 6–7×, and maintains competitive fidelity (PSNR > 26 dB, SSIM ≈ 0.80), bringing practical real-time novel view synthesis closer to deployable AR/VR systems. (Less)
Please use this url to cite or link to this publication:
author
Maithani, Garima LU
supervisor
organization
course
MAMM15 20251
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Real-time Rendering, 3D reconstruction, Gaussian Splatting, Novel View Synthesis, Neural Radiance Fields, Virtual Reality, Augmented Reality, Artificial Intelligence, Machine Learning
language
English
id
9215547
date added to LUP
2025-11-19 10:08:19
date last changed
2025-11-19 10:08:19
@misc{9215547,
  abstract     = {{Real-time 3D reconstruction is crucial for immersive AR/VR but is hard to achieve with traditional photogrammetry and mesh-based pipelines due to latency and limited scalability. Neural Radiance Fields (NeRF) enable high-quality novel view synthesis but suffer from long training and slow rendering, while Gaussian Splatting (GS) achieves real-time rendering at the cost of heavy preprocessing and memory usage. This thesis presents a comparative study of NeRF and GS in terms of visual quality, efficiency, and scalability, and proposes an optimized GS-based pipeline for real-time AR/VR. The system introduces three main techniques: (1) clustering-based reduction of COLMAP points to cut preprocessing to under two minutes; (2) gradient-aware clustering of Spherical Harmonic coefficients to shrink storage; and (3) quantization-aware training to reduce precision and memory requirements without harming visual quality. The optimized pipeline lowers total processing time to as little as 5 minutes, reaches up to 180 FPS at 1080p, reduces model size by 6–7×, and maintains competitive fidelity (PSNR > 26 dB, SSIM ≈ 0.80), bringing practical real-time novel view synthesis closer to deployable AR/VR systems.}},
  author       = {{Maithani, Garima}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Real-Time Rendering for AR/VR with Novel View Synthesis}},
  year         = {{2025}},
}