EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Path-Traced Inverse Rendering with Global Illumination in 3D Gaussian Fields

Junke Zhu, Hao Zhang, Yutian Zhu, Ang Li, Chenxiao Hu, Meng Gai, Fei Zhu, Zhangjin Huang, Sheng Li

ACM Transactions on Graphics · 09.11.2026 · 45 (6) · 1-14

DOI: 10.1145/3842545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 09.11.2026. Verfasst von Junke Zhu und 8 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ray tracing enables 3D Gaussian fields to serve as a representation for physically based light transport. Faithful inverse rendering requires forward rendering and backward optimization to be defined within a consistent light-transport pipeline. Existing Gaussian inverse-rendering methods typically rely on splatting-derived G-buffers and screen-space optimization. The local affine approximation of perspective projection can introduce inconsistencies with path tracing, while simplified rendering formulations often neglect or approximate indirect illumination and visibility. Therefore, we propose a splatting-free path-traced inverse-rendering framework for 3D Gaussian fields that unifies forward rendering and backward optimization within the same recursive multi-bounce light-transport pipeline. We formulate light transport over overlapping Gaussian primitives directly in path space, enabling Monte Carlo path tracing and pathwise gradient replay over the same recursively sampled transport paths. The framework jointly optimizes materials and environment light under the full rendering equation, with ray-traced visibility and global illumination explicitly evaluated. Extensive experiments demonstrate competitive material estimation and improved path-traced rendering quality, producing more plausible shadows, reflections, and relighting under global illumination. The code is available at https://junkzhu.github.io/project_pages/PTIR.

Zitieren

APA

Zhu, J., Zhang, H., Zhu, Y., Li, A., Hu, C., Gai, M., Zhu, F., Huang, Z., & Li, S. (2026). Path-Traced Inverse Rendering with Global Illumination in 3D Gaussian Fields. ACM Transactions on Graphics, 45(6), 1-14. https://doi.org/10.1145/3842545

Vancouver

Zhu J, Zhang H, Zhu Y, Li A, Hu C, Gai M, et al. Path-Traced Inverse Rendering with Global Illumination in 3D Gaussian Fields. ACM Transactions on Graphics. 2026;45(6):1-14. doi:10.1145/3842545

BibTeX
@article{Zhu2026,
  author = {Zhu, Junke and Zhang, Hao and Zhu, Yutian and Li, Ang and Hu, Chenxiao and Gai, Meng and Zhu, Fei and Huang, Zhangjin and Li, Sheng},
  title = {Path-Traced Inverse Rendering with Global Illumination in 3D Gaussian Fields},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {6},
  pages = {1--14},
  doi = {10.1145/3842545}
}
Kostenlos starten →