NeuS-PIR: Learning relightable neural surface using pre-integrated rendering

In this paper, we propose NeuS-PIR, a novel approach for learning relightable neural surfaces using pre-integrated rendering from multi-view image observations. Unlike traditional methods based on NeRFs or discrete mesh representations, our approach employs an implicit neural surface representation...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Shi Mao, Chenming Wu, Zhelun Shen, Yifan Wang, Dayan Wu, Liangjun Zhang
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Tsinghua University Press 2025-08-01
Edice:	Computational Visual Media
Témata:	inverse rendering pre-integrated rendering neural implicit representation
On-line přístup:	https://www.sciopen.com/article/10.26599/CVM.2025.9450493
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!