logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Importance sampling Guided Neural Radiosity

delete2025-11-05
delete0
PRE
AI
H
Huangsheng Du
Y
Youcheng Cai *
Y
Yutian Zhu
P
Peifeng Li
DOI：10.1016/j.cag.2025.104472delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• We present an Importance Sampling Guided Neural Radiosity framework that jointly optimizes the importance sampling module and the Neural Radiosity module, achieving both efficiency and effectiveness. • We propose an Improved Kullback–Leibler (IKL) divergence loss to mitigate the gradient conflict problem and further improve the convergence rate.

Journal

C
computers & graphics
IF:
0
Papers:
119
Citations:
0

Organization

No organization information available