5 papers · 1 filter
Compact Neural Appearance Models for Efficient Gaussian Splatting
Florian Hahlbohm, Jorge Condor, Linus Franke +2
Explicit primitive-based radiance fields such as 3D Gaussian Splatting typically model view-dependent appearance using low-order spherical harmonics (SH). Although efficient to eva…
Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction
Ewa Miazga, Jorge Condor, Piotr Didyk
View-dependent appearance modeling remains a challenging problem in novel-view synthesis and reconstruction. Accurately representing complex angular effects often requires substant…
Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
Jorge Condor, Nicolas Moenne-Loccoz, Merlin Nimier-David +3
Primitive-based methods such as 3D Gaussian Splatting have recently become the state-of-the-art for novel-view synthesis and related reconstruction tasks. Compared to neural fields…
Human Vision Constrained Super-Resolution
Volodymyr Karpenko, Taimoor Tariq, Jorge Condor +1
Modern deep-learning super-resolution (SR) techniques process images and videos independently of the underlying content and viewing conditions. However, the sensitivity of the huma…
Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions
Nicolai Hermann, Jorge Condor, Piotr Didyk
Modern reconstruction techniques can effectively model complex 3D scenes from sparse 2D views. However, automatically assessing the quality of novel views and identifying artifacts…