5 papers
GScomp-QA: A Subjective Dataset for Quality Assessment of Compressed Gaussian Splatting
Pedro Martin, António Rodrigues, João Ascenso +1
Gaussian Splatting (GS) has emerged as an efficient representation for high-quality 3D reconstruction and novel view synthesis. However, its large model size poses challenges for s…
Structured Image-based Coding for Efficient Gaussian Splatting Compression
Pedro Martin, Antonio Rodrigues, Joao Ascenso +1
Gaussian Splatting (GS) has recently emerged as a state-of-the-art representation for radiance fields, combining real-time rendering with high visual fidelity. However, GS models r…
GS-QA: Comprehensive Quality Assessment Benchmark for Gaussian Splatting View Synthesis
Pedro Martin, António Rodrigues, João Ascenso +1
Gaussian Splatting (GS) offers a promising alternative to Neural Radiance Fields (NeRF) for real-time 3D scene rendering. Using a set of 3D Gaussians to represent complex geometry…
NeRF-QA: Neural Radiance Fields Quality Assessment Database
Pedro Martin, António Rodrigues, João Ascenso +1
This short paper proposes a new database - NeRF-QA - containing 48 videos synthesized with seven NeRF based methods, along with their perceived quality scores, resulting from subje…
Evaluation of strategies for efficient rate-distortion NeRF streaming
Pedro Martin, António Rodrigues, João Ascenso +1
Neural Radiance Fields (NeRF) have revolutionized the field of 3D visual representation by enabling highly realistic and detailed scene reconstructions from a sparse set of images.…