Presentation

<
ZeroGrads: Learning Local Surrogates for Non-differentiable Graphics
SessionDifferentiable Rendering
DescriptionZeroGrads learns a mapping between a graphic pipeline's input parameters and the corresponding loss. The gradient of this mapping can then be used for inverse optimization, enabling the optimization of black-box graphics problems.
Authors
Michael Fischer
University College London (UCL)
Tobias Ritschel
University College London (UCL)
Event Type
Technical Paper
TimeMonday, 29 July 20242:30pm - 2:40pm MDT
LocationMile High 4
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Monday, 29 July 20242:00pm - 3:30pm MDTMile High 4
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Machine Learning
Rendering
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Monday
Next PresentationNext PresentationView-Independent Adjoint Light Tracing for Lighting Design Optimization