Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphics

arXiv:2308.05739v2 Announce Type: replace-cross
Abstract: Gradient-based optimization is now ubiquitous across graphics, but unfortunately can not be applied to problems with undefined or zero gradients. To circumvent this issue, the loss function can be manually replaced by a ``surrogate'' that has similar minima but is differentiable. Our proposed framework, ZeroGrads, automates this process by learning a neural approximation of the objective function, which in turn can be used to differentiate through arbitrary black-box graphics pipelines. We train the surrogate on …

abstract arxiv cs.cv cs.gr cs.lg differentiable framework function gradient graphics issue loss losses optimization type