8 papers
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…
Gabor Fields: Orientation-Selective Level-of-Detail for Volume Rendering
Jorge Condor, Nicolai Hermann, Mehmet Ata Yurtsever +1
Gaussian-based representations have enabled efficient physically-based volume rendering at a fraction of the memory cost of regular, discrete, voxel-based distributions. However, s…
Temporal Brightness Management for Immersive Content
Luca Surace, Jorge Condor, Piotr Didyk
Modern virtual reality headsets demand significant computational resources to render high-resolution content in real-time. Therefore, prioritizing power efficiency becomes crucial,…
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…