EUVIMEDEUVIMED entdecken
Crossref

MILO: Multi-Bounce Inverse Rendering for Indoor Scene With Light-Emitting Objects

Bohan Yu, Siqi Yang, Xuanning Cui, Siyan Dong, Baoquan Chen, Boxin Shi

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-08 · 45 (8) · 10129-10142

DOI: 10.1109/tpami.2023.3244658 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-08. Verfasst von Bohan Yu und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Algorithms, Lighting. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Collaborative Innovation Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, many advances in inverse rendering are achieved by high-dimensional lighting representations and differentiable rendering. However, multi-bounce lighting effects can hardly be handled correctly in scene editing using high-dimensional lighting representations, and light source model deviation and ambiguities exist in differentiable rendering methods. These problems limit the applications of inverse rendering. In this paper, we present a multi-bounce inverse rendering method based on Monte Carlo path tracing, to enable correct complex multi-bounce lighting effects rendering in scene editing. We propose a novel light source model that is more suitable for light source editing in indoor scenes, and design a specific neural network with corresponding disambiguation constraints to alleviate ambiguities during the inverse rendering. We evaluate our method on both synthetic and real indoor scenes through virtual object insertion, material editing, relighting tasks, and so on. The results demonstrate that our method achieves better photo-realistic quality.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsLightingNeural Networks, ComputerMonte Carlo Method

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Collaborative Innovation Program

Zitieren

APA

Yu, B., Yang, S., Cui, X., Dong, S., Chen, B., & Shi, B. (2023). MILO: Multi-Bounce Inverse Rendering for Indoor Scene With Light-Emitting Objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8), 10129-10142. https://doi.org/10.1109/tpami.2023.3244658

Vancouver

Yu B, Yang S, Cui X, Dong S, Chen B, Shi B. MILO: Multi-Bounce Inverse Rendering for Indoor Scene With Light-Emitting Objects. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(8):10129-10142. doi:10.1109/tpami.2023.3244658

BibTeX
@article{Yu2023,
  author = {Yu, Bohan and Yang, Siqi and Cui, Xuanning and Dong, Siyan and Chen, Baoquan and Shi, Boxin},
  title = {MILO: Multi-Bounce Inverse Rendering for Indoor Scene With Light-Emitting Objects},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {8},
  pages = {10129--10142},
  doi = {10.1109/tpami.2023.3244658}
}
Kostenlos starten →