OUIII

The Visual Language of Fabrics

Conference or journal: Siggraph 2023 Date : 2023.07 Valentin Deschaintre*, Julia Guerrero-Viu*, Diego Gutierrez, Tamy Boubekeur, Belen MasiaWe introduce text2fabric, a novel dataset that links free-text descriptions to various fabric materials. The dataset comprises 15,000 natural language descriptions associated to …

OUIII

Wide Gamut Moment-based Constrained Spectral Uplifting

Conference or journal: Computer Graphics Forum Vol 41(2022) Date : 2022.07 Lucia Tódová, A. Wilkie, L. Fascione.Spectral rendering is increasingly used in appearance-critical rendering workflows due to its ability to predict colour values under varying illuminants. However, directly modelling assets …

OUIII

Perceptual error optimization for Monte Carlo animation rendering

Conference or journal: SIGGRAPH Asia 2023 Date : 2023.11 Miša Korać, Corentin Salaün, Iliyan Georgiev, Pascal Grittmann, Philipp Slusallek, Karol Myszkowski, Gurprit SinghIndependently estimating pixel values in Monte Carlo rendering results in a perceptually sub-optimal white-noise distribution of error in …

OUIII

Practical Temporal and Stereoscopic Filtering for Real-time Ray Tracing

Conference or journal: Eurographics Symposium on Rendering (2023) Date : 2023.06 Henrik Philippi, Jeppe Revall Frisvad, Henrik Wann JensenWe present a practical method for temporal and stereoscopic filtering that generates stereo-consistent rendering. Existing methods for stereoscopic rendering often reuse samples …

OUIII

Rendering Glinty Granular Materials in Virtual Reality

Conference or journal: ICAT-EGVE 2022 Date : 2022.12 Nynne Kajs, Mikkel Gjøl, Jakob Gath, Henrik Philippi, Jeppe Revall Frisvad, Andreas BærentzenHighly realistic rendering of grainy materials like sand is achievable given significant computational resources and a lot of time for …

OUIII

Denoising-Aware Adaptive Sampling for Monte Carlo Ray Tracing

Conference or journal: SIGGRAPH 2023 Date : 2023.07 Arthur Firmino, Jeppe Revall Frisvad, Henrik Wann JensenMonte Carlo rendering is a computationally intensive task, but combined with recent deep-learning based advances in image denoising it is possible to achieve high quality …