Diffusion Posterior Illumination for Ambiguity-Aware Inverse Rendering
ACM Transactions on Graphics · 05.12.2023 · 42 (6) · 1-14
DOI: 10.1145/3618357 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 05.12.2023. Verfasst von Linjie Lyu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 69 Literaturangaben.
Abstract (Originalsprache)
Inverse rendering, the process of inferring scene properties from images, is a challenging inverse problem. The task is ill-posed, as many different scene configurations can give rise to the same image. Most existing solutions incorporate priors into the inverse-rendering pipeline to encourage plausible solutions, but they do not consider the inherent ambiguities and the multi-modal distribution of possible decompositions. In this work, we propose a novel scheme that integrates a denoising diffusion probabilistic model pre-trained on natural illumination maps into an optimization framework involving a differentiable path tracer. The proposed method allows sampling from combinations of illumination and spatially-varying surface materials that are, both, natural and explain the image observations. We further conduct an extensive comparative study of different priors on illumination used in previous work on inverse rendering. Our method excels in recovering materials and producing highly realistic and diverse environment map samples that faithfully explain the illumination of the input images.
Zitieren
APA
Lyu, L., Tewari, A., Habermann, M., Saito, S., Zollhöfer, M., Leimkühler, T., & Theobalt, C. (2023). Diffusion Posterior Illumination for Ambiguity-Aware Inverse Rendering. ACM Transactions on Graphics, 42(6), 1-14. https://doi.org/10.1145/3618357
Vancouver
Lyu L, Tewari A, Habermann M, Saito S, Zollhöfer M, Leimkühler T, et al. Diffusion Posterior Illumination for Ambiguity-Aware Inverse Rendering. ACM Transactions on Graphics. 2023;42(6):1-14. doi:10.1145/3618357
BibTeX
@article{Lyu2023,
author = {Lyu, Linjie and Tewari, Ayush and Habermann, Marc and Saito, Shunsuke and Zollhöfer, Michael and Leimkühler, Thomas and Theobalt, Christian},
title = {Diffusion Posterior Illumination for Ambiguity-Aware Inverse Rendering},
journal = {ACM Transactions on Graphics},
year = {2023},
volume = {42},
number = {6},
pages = {1--14},
doi = {10.1145/3618357}
}
EUVIMED