Browsing by Author "Patney, Anjul"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Detecting Aliasing Artifacts in Image Sequences Using Deep Neural Networks
    (ACM, 2018) Patney, Anjul; Lefohn, Aaron; Patney, Anjul and Niessner, Matthias
    In this short paper we present a machine learning approach to detect visual artifacts in rendered image sequences. Specifically, we train a deep neural network using example aliased and antialiased image sequences exported from a real-time renderer. The trained network learns to identify and locate aliasing artifacts in an input sequence, without comparing it against a ground truth. Thus, it is useful as a fully automated tool for evaluating image quality. We demonstrate the effectiveness of our approach in detecting aliasing in several rendered sequences. The trained network correctly predicts aliasing in 64×64×4 animated sequences with more than 90% accuracy for images it hasn't seen before. The output of our network is a single scalar between 0 and 1, which is usable as a quality metric for aliasing. It follows the same trend as (1-SSIM) for images with increasing sample counts.
  • Thumbnail Image
    Item
    Neural Temporal Adaptive Sampling and Denoising
    (The Eurographics Association and John Wiley & Sons Ltd., 2020) Hasselgren, Jon; Munkberg, Jacob; Salvi, Marco; Patney, Anjul; Lefohn, Aaron; Panozzo, Daniele and Assarsson, Ulf
    Despite recent advances in Monte Carlo path tracing at interactive rates, denoised image sequences generated with few samples per-pixel often yield temporally unstable results and loss of high-frequency details. We present a novel adaptive rendering method that increases temporal stability and image fidelity of low sample count path tracing by distributing samples via spatio-temporal joint optimization of sampling and denoising. Adding temporal optimization to the sample predictor enables it to learn spatio-temporal sampling strategies such as placing more samples in disoccluded regions, tracking specular highlights, etc; adding temporal feedback to the denoiser boosts the effective input sample count and increases temporal stability. The temporal approach also allows us to remove the initial uniform sampling step typically present in adaptive sampling algorithms. The sample predictor and denoiser are deep neural networks that we co-train end-to-end over multiple consecutive frames. Our approach is scalable, allowing trade-off between quality and performance, and runs at near real-time rates while achieving significantly better image quality and temporal stability than previous methods.