39-Issue 4

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632924

Browse

Browsing 39-Issue 4 by Subject "Neural networks"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    High-Resolution Neural Face Swapping for Visual Effects
    (The Eurographics Association and John Wiley & Sons Ltd., 2020) Naruniec, Jacek; Helminger, Leonhard; Schroers, Christopher; Weber, Romann M.; Dachsbacher, Carsten and Pharr, Matt
    In this paper, we propose an algorithm for fully automatic neural face swapping in images and videos. To the best of our knowledge, this is the first method capable of rendering photo-realistic and temporally coherent results at megapixel resolution. To this end, we introduce a progressively trained multi-way comb network and a light- and contrast-preserving blending method. We also show that while progressive training enables generation of high-resolution images, extending the architecture and training data beyond two people allows us to achieve higher fidelity in generated expressions. When compositing the generated expression onto the target face, we show how to adapt the blending strategy to preserve contrast and low-frequency lighting. Finally, we incorporate a refinement strategy into the face landmark stabilization algorithm to achieve temporal stability, which is crucial for working with high-resolution videos. We conduct an extensive ablation study to show the influence of our design choices on the quality of the swap and compare our work with popular state-of-the-art methods.
  • Thumbnail Image
    Item
    Neural Denoising with Layer Embeddings
    (The Eurographics Association and John Wiley & Sons Ltd., 2020) Munkberg, Jacob; Hasselgren, Jon; Dachsbacher, Carsten and Pharr, Matt
    We propose a novel approach for denoising Monte Carlo path traced images, which uses data from individual samples rather than relying on pixel aggregates. Samples are partitioned into layers, which are filtered separately, giving the network more freedom to handle outliers and complex visibility. Finally the layers are composited front-to-back using alpha blending. The system is trained end-to-end, with learned layer partitioning, filter kernels, and compositing. We obtain similar image quality as recent state-of-the-art sample based denoisers at a fraction of the computational cost and memory requirements.
  • Thumbnail Image
    Item
    Photorealistic Material Editing Through Direct Image Manipulation
    (The Eurographics Association and John Wiley & Sons Ltd., 2020) Zsolnai-Fehér, Károly; Wonka, Peter; Wimmer, Michael; Dachsbacher, Carsten and Pharr, Matt
    Creating photorealistic materials for light transport algorithms requires carefully fine-tuning a set of material properties to achieve a desired artistic effect. This is typically a lengthy process that involves a trained artist with specialized knowledge. In this work, we present a technique that aims to empower novice and intermediate-level users to synthesize high-quality photorealistic materials by only requiring basic image processing knowledge. In the proposed workflow, the user starts with an input image and applies a few intuitive transforms (e.g., colorization, image inpainting) within a 2D image editor of their choice, and in the next step, our technique produces a photorealistic result that approximates this target image. Our method combines the advantages of a neural network-augmented optimizer and an encoder neural network to produce high-quality output results within 30 seconds. We also demonstrate that it is resilient against poorly-edited target images and propose a simple extension to predict image sequences with a strict time budget of 1-2 seconds per image.