The Next Frontier POTENTIAL RESEARCH IDEAS Gradientdomain virtual

POTENTIAL RESEARCH IDEAS • Gradient-domain virtual point lights and scalable many lights rendering. •

POTENTIAL RESEARCH IDEAS • Unifying points, beams, and other integrators for volumetric rendering into

POTENTIAL RESEARCH IDEAS • Robust shift mapping and reconstruction. • Integrate path guiding. •

POTENTIAL RESEARCH IDEAS • Simpler implementation of gradientdomain bidirectional techniques. • Gradient-domain rendering in

ACKNOWLEDGEMENT We are grateful to all authors of gradient-domain rendering for making their source

ACKNOWLEDGEMENT We also thank the following researchers: • • Wenzel Jakob for the Mitsuba

ACKNOWLEDGEMENT We thank the following researchers and artists for making the beautiful scenes: •

ACKNOWLEDGEMENT This project was partly funded by • JSPS KAKENHI grant numbers 15 H

Slides: 9

Download presentation

The Next Frontier

POTENTIAL RESEARCH IDEAS • Gradient-domain virtual point lights and scalable many lights rendering. • Gradient-domain photon density estimation in splatting style.

POTENTIAL RESEARCH IDEAS • Unifying points, beams, and other integrators for volumetric rendering into a single gradient-domain integrator, i. e. , gradient-domain UPBP. • Rendering heterogeneous media with gradient-domain techniques.

POTENTIAL RESEARCH IDEAS • Robust shift mapping and reconstruction. • Integrate path guiding. • Very low sample count gradientdomain rendering. • Combine image-space denoisers with gradient-domain rendering.

POTENTIAL RESEARCH IDEAS • Simpler implementation of gradientdomain bidirectional techniques. • Gradient-domain rendering in production. • Accelerating gradient-domain rendering on the GPU and for realtime applications.

ACKNOWLEDGEMENT We are grateful to all authors of gradient-domain rendering for making their source code available. We also thank the following authors for the permission to include materials from their publications into the course: • Jaakko Lehtinen, Aalto University and NVIDIA • Derek Nowrouzezahrai, Mc. Gill University • Elmar Eisemann, Delft University of Technology • Bochang Moon, Gwangju Institute of Science and Technology

ACKNOWLEDGEMENT We also thank the following researchers: • • Wenzel Jakob for the Mitsuba renderer. Fabrice Rousselle for some presentation slides of image denoisers we derived.

ACKNOWLEDGEMENT We thank the following researchers and artists for making the beautiful scenes: • • Eric Veach, Leo Guibas, Miika Aittala, Samuli Laine, and Jaakko Lehtinen (the Door scene) Jay. Artist (Kitchen) Wig 42 (Staircase) Mareck (Bathroom) Chaos Group and Jaroslav Krivanek (Spotlight bathroom) Marko Dabrovic (Sponza) Tiziano Portenier (Bookshelf, Bottle, and Bathroom)

ACKNOWLEDGEMENT This project was partly funded by • JSPS KAKENHI grant numbers 15 H 05308 and 17 K 19958 • Swiss National Science Foundation grant number 163045