Expressive + WICED 2025: Artworks, Posters, and Demo

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3607142

Browse

Browsing Expressive + WICED 2025: Artworks, Posters, and Demo by Subject "Computing methodologies → Non"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Evaluating Temporal Coherence using a Watercolor Renderer
    (The Eurographics Association, 2025) Morgan, Ingrid Ellen Carr; Billeter, Markus; Anjyo, Ken; Anjos, Rafael Kuffner dos; Berio, Daniel; Bruckert, Alexandre
    Temporal coherence is a long-standing issue within Non-Photorealistic Rendering (NPR). The problem has been defined as a trade-off between the three main factors: flatness, temporal continuity and motion coherence. Approaches that improve temporal coherence are applied across different styles within diverse animation contexts. We have implemented a watercolour renderer that supports multiple temporal coherence approaches in a unified system to investigate this trade-off. The approaches are then evaluated against existing work, with consideration of how external factors including animations and textures may influence perceived incoherence.
  • Thumbnail Image
    Item
    Robotic Painting using Semantic Image Abstraction
    (The Eurographics Association, 2025) Stroh, Michael; Paetzold, Patrick; Berio, Daniel; Leymarie, Frederic Fol; Kehlbeck, Rebecca; Deussen, Oliver; Berio, Daniel; Bruckert, Alexandre
    We present a novel image segmentation and abstraction pipeline tailored to robot painting applications. We address the unique challenges of realizing digital abstractions as physical artistic renderings. Our approach generates adaptive, semantics-based abstractions that balance aesthetic appeal, structural coherence, and practical constraints inherent to robotic systems. By integrating panoptic segmentation with color-based over-segmentation, we partition images into meaningful regions corresponding to semantic objects while providing customizable abstraction levels we optimize for robotic realization. We employ saliency maps and color difference metrics to support automatic parameter selection to guide a merging process that detects and preserves critical object boundaries while simplifying less salient areas. Graph-based community detection further refines the abstraction by grouping regions based on local connectivity and semantic coherence. These abstractions enable robotic systems to create paintings on real canvases with a controlled level of detail and abstraction.