Browsing by Author "Herveau, Killian"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Minimal Convolutional Neural Networks for Temporal Anti Aliasing
    (The Eurographics Association, 2023) Herveau, Killian; Piochowiak, Max; Dachsbacher, Carsten; Bikker, Jacco; Gribble, Christiaan
    Existing deep learning methods for performing temporal anti aliasing (TAA) in rendering are either closed source or rely on upsampling networks with a large operation count which are expensive to evaluate. We propose a simple deep learning architecture for TAA combining only a few common primitives, easy to assemble and to change for application needs. We use a fully-convolutional neural network architecture with recurrent temporal feedback, motion vectors and depth values as input and show that a simple network can produce satisfactory results. Our architecture template, for which we provide code, introduces a method that adapts to different temporal subpixel offsets for accumulation without increasing the operation count. To this end, convolutional layers cycle through a set of different weights per temporal subpixel offset while their operations remain fixed. We analyze the effect of this method on image quality and present different tradeoffs for adapting the architecture. We show that our simple network performs remarkably better than variance clipping TAA, eliminating both flickering and ghosting without performing upsampling.
  • No Thumbnail Available
    Item
    Out-of-the-loop Autotuning of Metropolis Light Transport with Reciprocal Probability Binning
    (The Eurographics Association, 2023) Herveau, Killian; Otsu, Hisanari; Dachsbacher, Carsten; Babaei, Vahid; Skouras, Melina
    The performance of Markov Chain Monte Carlo (MCMC) rendering methods depends heavily on the mutation strategies and their parameters. We treat the underlying mutation strategies as black-boxes and focus on their parameters. This avoids the need for tedious manual parameter tuning and enables automatic adaptation to the actual scene. We propose a framework for out-of-the-loop autotuning of these parameters. As a pilot example, we demonstrate our tuning strategy for small-step mutations in Primary Sample Space Metropolis Light Transport. Our σ-binning strategy introduces a set of mutation parameters chosen by a heuristic: the inverse probability of the local direction sampling, which captures some characteristics of the local sampling. We show that our approach can successfully control the parameters and achieve better performance compared to non-adaptive mutation strategies.