% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Rolff:599818,
      author       = {Rolff, Tim and Schmidt, Susanne and Li, Ke and Steinicke,
                      Frank and Frintrop, Simone},
      title        = {{VRS}-{N}e{RF}: {A}ccelerating {N}eural {R}adiance {F}ield
                      {R}endering with {V}ariable {R}ate {S}hading},
      publisher    = {IEEE},
      reportid     = {PUBDB-2023-07544},
      pages        = {243 - 252},
      year         = {2023},
      comment      = {2023 IEEE International Symposium on Mixed and Augmented
                      Reality (ISMAR) : [Proceedings] - IEEE, 2023. - ISBN
                      979-8-3503-2838-7 - doi:10.1109/ISMAR59233.2023.00039},
      booktitle     = {2023 IEEE International Symposium on
                       Mixed and Augmented Reality (ISMAR) :
                       [Proceedings] - IEEE, 2023. - ISBN
                       979-8-3503-2838-7 -
                       doi:10.1109/ISMAR59233.2023.00039},
      abstract     = {Recent advancements in Neural Radiance Fields (NeRF)
                      provide enormous potential for a wide range of Mixed Reality
                      (MR) applications. However, the applicability of NeRF to
                      real-time MR systems is still largely limited by the
                      rendering performance of NeRF. In this paper, we present a
                      novel approach for Variable Rate Shading for Neural Radiance
                      Fields (VRS-NeRF). In contrast to previous techniques, our
                      approach does not require training multiple neural networks
                      or re-training of already existing ones, but instead
                      utilizes the raytracing properties of NeRF. This is achieved
                      by merging rays depending on a variable shading rate, which
                      reduces the overall number of queries to the neural network.
                      We demonstrate the generalizability of our approach by
                      implementing three alternative functions for the
                      determination of the shading rate. The first method uses the
                      gaze of users to effectively implement a foveated rendering
                      technique in NeRF. For the other two techniques, we utilize
                      shading rates based on edges and saliency. Based on a
                      psychophysical experiment and multiple image-based metrics,
                      we suggest a set of parameters for each technique, yielding
                      an optimal tradeoff between rendering performance gain and
                      perceived visual quality.},
      month         = {Oct},
      date          = {2023-10-16},
      organization  = {2023 IEEE International Symposium on
                       Mixed and Augmented Reality, Sydney
                       (Australia), 16 Oct 2023 - 20 Oct 2023},
      cin          = {MCS},
      cid          = {I:(DE-H253)MCS-20120806},
      pnm          = {621 - Accelerator Research and Development (POF4-621) /
                      HIDSS-0002 - DASHH: Data Science in Hamburg - Helmholtz
                      Graduate School for the Structure of Matter
                      $(2019_IVF-HIDSS-0002)$},
      pid          = {G:(DE-HGF)POF4-621 / $G:(DE-HGF)2019_IVF-HIDSS-0002$},
      experiment   = {EXP:(DE-MLZ)NOSPEC-20140101},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.1109/ISMAR59233.2023.00039},
      url          = {https://bib-pubdb1.desy.de/record/599818},
}