Annalena UlschmidORCID iD, Bernhard KerblORCID iD, Katharina KröslORCID iD, Michael WimmerORCID iD
Real-Time Editing of Path-Traced Scenes with Prioritized Re-Rendering
In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - GRAPP and VISIGRAPP, pages 46-57. February 2024.
[paper] [GitHub]

Information

  • Publication Type: Conference Paper
  • Workgroup(s)/Project(s):
  • Date: February 2024
  • ISBN: 978-989-758-679-8
  • Note: Best student paper award
  • Location: Rom
  • Lecturer: Annalena UlschmidORCID iD
  • Event: 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
  • Editor: Bashford-Rogers, Thomas and Meneveaux, Daniel and Ziat, Mounia and Ammi, Mehdi and Jänicke, Stefan and Purchase, Helen and Bouatouch, Kadi and Sousa, Augusto A.
  • DOI: 10.5220/0012324600003660
  • Booktitle: Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - GRAPP and VISIGRAPP
  • Pages: 12
  • Conference date: 27. February 2024 – 29. February 2024
  • Pages: 46 – 57
  • Keywords: ray tracing, user study, editing

Abstract

With recent developments in GPU ray tracing performance and (AI-accelerated) noise reduction techniques, Monte Carlo Path Tracing at real-time rates becomes a viable solution for interactive 3D scene editing, with growing support in popular software. However, even for minor edits (e.g., adjusting materials or moving small objects), current solutions usually discard previous samples and the image formation process is started from scratch. In this paper, we present two adaptive, priority-based re-rendering techniques with incremental updates, prioritizing the reconstruction of regions with high importance, before gradually moving to less important regions. The suggested methods automatically identify and schedule sampling and accumulation of immediately affected regions. An extensive user study analyzes whether such prioritized renderings are beneficial to interactive scene editing, comparing them with same-time conventional re-rendering. Our evaluation shows that even with simple prio rity policies, there is a significant preference for such incremental rendering techniques for interactive editing of small objects over full-screen re-rendering with denoising.

Additional Files and Images

Additional images and videos

Additional files

Weblinks

BibTeX

@inproceedings{ulschmid-2024-reo,
  title =      "Real-Time Editing of Path-Traced Scenes with Prioritized
               Re-Rendering",
  author =     "Annalena Ulschmid and Bernhard Kerbl and Katharina Kr\"{o}sl
               and Michael Wimmer",
  year =       "2024",
  abstract =   "With recent developments in GPU ray tracing performance and
               (AI-accelerated) noise reduction techniques, Monte Carlo
               Path Tracing at real-time rates becomes a viable solution
               for interactive 3D scene editing, with growing support in
               popular software. However, even for minor edits (e.g.,
               adjusting materials or moving small objects), current
               solutions usually discard previous samples and the image
               formation process is started from scratch. In this paper, we
               present two adaptive, priority-based re-rendering techniques
               with incremental updates, prioritizing the reconstruction of
               regions with high importance, before gradually moving to
               less important regions. The suggested methods automatically
               identify and schedule sampling and accumulation of
               immediately affected regions. An extensive user study
               analyzes whether such prioritized renderings are beneficial
               to interactive scene editing, comparing them with same-time
               conventional re-rendering. Our evaluation shows that even
               with simple prio rity policies, there is a significant
               preference for such incremental rendering techniques for
               interactive editing of small objects over full-screen
               re-rendering with denoising.",
  month =      feb,
  isbn =       "978-989-758-679-8",
  note =       "Best student paper award",
  location =   "Rom",
  event =      "19th International Joint Conference on Computer Vision,
               Imaging and Computer Graphics Theory and Applications",
  editor =     "Bashford-Rogers, Thomas and Meneveaux, Daniel and Ziat,
               Mounia and Ammi, Mehdi and J\"{a}nicke, Stefan and Purchase,
               Helen and Bouatouch, Kadi and Sousa, Augusto A.",
  doi =        "10.5220/0012324600003660",
  booktitle =  "Proceedings of the 19th International Joint Conference on
               Computer Vision, Imaging and Computer Graphics Theory and
               Applications - GRAPP and VISIGRAPP",
  pages =      "12",
  pages =      "46--57",
  keywords =   "ray tracing, user study, editing",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2024/ulschmid-2024-reo/",
}