BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190105Z
LOCATION:West Building\, Rooms 301-305
DTSTART;TZID=America/Los_Angeles:20250812T140000
DTEND;TZID=America/Los_Angeles:20250812T153000
UID:siggraph_SIGGRAPH 2025_sess131@linklings.com
SUMMARY:Differentiable & Inverse Rendering
DESCRIPTION:Differentiable & Inverse Rendering - Interactive Discussion\n\
 nAfter the summary presentations, attendees will participate in an interac
 tive discussion. Outside the room will be a series of poster boards for au
 thors to gather around with the audience. Authors are invited to bring any
  material related to their paper that could instigate further conversation
  such...\n\n---------------------\nImage-space Adaptive Sampling for Fast 
 Inverse Rendering\n\nOur goal is to accelerate inverse rendering by reduci
 ng the sampling budget without sacrificing overall performance. We introdu
 ce a novel image-space adaptive sampling framework to accelerate inverse r
 endering by dynamically adjusting pixel sampling probabilities based on gr
 adient variance and contr...\n\n\nKai Yan (University of California Irvine
 ); Cheng Zhang (Reality Labs Research, Meta); Sébastien Speierer (Reality 
 Labs, Meta); Guangyan Cai (University of California Irvine); Yufeng Zhu an
 d Zhao Dong (Reality Labs, Meta); and Shuang Zhao (University of Californi
 a Irvine)\n---------------------\nDifferentiable Geometric Acoustic Path T
 racing using Time-Resolved Path Replay Backpropagation\n\nIntroducing diff
 erentiable path tracing for geometric acoustics with an efficient gradient
  algorithm based on path replay backpropagation. The system computes deriv
 atives of output spectrograms with respect to arbitrary scene parameters (
 materials, geometry, emitters, microphones) within the framewo...\n\n\nUgo
  Finnendahl, Markus Worchel, Tobias Jüterbock, Daniel Wujecki, Fabian Brin
 kmann, Stefan Weinzierl, and Marc Alexa (TU Berlin)\n---------------------
 \nQuadric-Based Silhouette Sampling for Differentiable Rendering\n\nPhysic
 ally based differentiable rendering computes gradients of the rendering eq
 uation. The task is made difficult by discontinuities in the integrand at 
 object silhouettes. To address this challenge, we propose a novel edge sam
 pling approach that outperforms the state-of-the-art among unidirectiona..
 .\n\n\nMariia Soroka (Cornell University, Intel); Christoph Peters (Delft 
 University of Technology, Intel); and Steve Marschner (Cornell University)
 \n---------------------\nJames-Stein Gradient Combiner for Inverse Monte C
 arlo Rendering\n\nThis paper introduces a gradient combiner that blends un
 biased and biased gradients in parameter space using the James-Stein estim
 ator to infer scene parameters (BSDFs and volumes) from images. This appro
 ach enhances optimization accuracy compared to relying solely on either un
 biased or biased gradi...\n\n\nJeongmin Gu and Bochang Moon (Gwangju Insti
 tute of Science and Technology)\n---------------------\nUnbiased Different
 ial Visibility Using Fixed-Step Walk-on-Spherical-Caps And Closest Silhoue
 ttes\n\nWarped-area reparameterization is a powerful technique to compute 
 differential visibility. The key is constructing a velocity field that is 
 continuous in the domain interior and agrees with defined velocities on bo
 undaries. We present a robust and efficient unbiased estimator for differe
 ntial visibi...\n\n\nLifan Wu, Nathan Morrical, Sai Praveen Bangaru, Rohan
  Sawhney, Shuang Zhao, Chris Wyman, Ravi Ramamoorthi, and Aaron Lefohn (NV
 IDIA)\n---------------------\nMoment Bounds are Differentiable: Efficientl
 y Approximating Measures in Inverse Rendering\n\nMeasures can be compactly
  represented and approximated using the theory of moments. This work prove
 s that such moment-based representations are differentiable, leading to pr
 incipled and efficient approaches for approximating transmittance and visi
 bility in differentiable rendering.\n\n\nMarkus Worchel and Marc Alexa (TU
  Berlin)\n\nInterest Area: Research & Education\n\nRecording: Livestreamed
 , Not Livestreamed, Recorded, Not Recorded\n\nRegistration Category: Full 
 Conference, Virtual Access, Tuesday\n\nSession Chair: Mengqi Xia (Yale Uni
 versity)
END:VEVENT
END:VCALENDAR