BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030656Z
LOCATION:Meeting Room S426+S427\, Level 4
DTSTART;TZID=Asia/Hong_Kong:20251216T112300
DTEND;TZID=Asia/Hong_Kong:20251216T113400
UID:siggraphasia_SIGGRAPH Asia 2025_sess118_papers_1797@linklings.com
SUMMARY:Imperfect Image-Space Control Variates for Monte Carlo Rendering
DESCRIPTION:Chanu Yang and Bochang Moon (Gwangju Institute of Science and 
 Technology)\n\nWe present an image-space control variate technique to impr
 ove Monte Carlo~(MC) integration-based rendering. Our method selects spati
 ally nearby pixel estimates as control variates to exploit spatial coheren
 ce among pixel estimates in a rendered image without requiring analytic mo
 deling of the control variate functions. Employing control variates is a c
 lassical and well-established technique for variance reduction in MC integ
 ration, typically relying on the assumption that the expectations of contr
 ol variates are readily obtainable. When this condition is met, control va
 riate theory offers a principled framework for optimizing their use by adj
 usting coefficients that determine the relative contribution of each contr
 ol variate. However, our image-space approach introduces a technical chall
 enge, as the expectations of the pixel-based control variates are unknown 
 and must be estimated from additional MC samples, which are unbiased but i
 nherently noisy. In this paper, we propose a control variate estimator des
 igned to optimally leverage such imperfect control variates by relaxing th
 e traditional requirement that their expectations are known. We demonstrat
 e that our approach, which estimates the optimal coefficients while explic
 itly accounting for uncertainty in the expectation estimates, effectively 
 reduces the variance of MC rendering across various test scenes.\n\nRegist
 ration Category: Full Access, Full Access Supporter\n\nSession Chair: Oliv
 er Deussen (University of Konstanz)\n\n
END:VEVENT
END:VCALENDAR