BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241205T094200
DTEND;TZID=Asia/Tokyo:20241205T095600
UID:siggraphasia_SIGGRAPH Asia 2024_sess125_papers_443@linklings.com
SUMMARY:Spatiotemporal Bilateral Gradient Filtering for Inverse Rendering
DESCRIPTION:Technical Papers\n\nWesley Chang, Xuanda Yang, Yash Belhe, Rav
 i Ramamoorthi, and Tzu-Mao Li (University of California San Diego)\n\nIn i
 nverse rendering, gradient-based methods, which have seen great progress i
 n the recent years, are typically used in conjunction with the Adam optimi
 zer. While Adam usually improves convergence by temporally filtering gradi
 ents over previous iterations to reduce noise, it is not tailored to inver
 se rendering where the target signals (textures, volumes, or geometry) are
  usually piecewise smooth. Previous work has applied the inverse Laplacian
  operator to smooth gradients spatially, but this isotropic filtering can 
 often lead to oversmoothing. We propose a spatiotemporal optimizer that ca
 n significantly speedup the convergence over Adam, by enforcing the optimi
 zation parameter updates to be piecewise smooth through a lightweight spat
 ial domain cross-bilateral filter. We discuss different options of combini
 ng spatial filtering and Adam's temporal filtering, and provide intuitions
  for different scenarios. We show that our filtering leads to significantl
 y higher-quality reconstructions in different inverse problems including t
 exture, volume and geometry recovery.\n\nRegistration Category: Full Acces
 s, Full Access Supporter\n\nLanguage Format: English Language\n\nSession C
 hair: Wenzel Jakob (École Polytechnique Fédérale de Lausanne)
URL:https://asia.siggraph.org/2024/program/?id=papers_443&sess=sess125
END:VEVENT
END:VCALENDAR