Segmentation-Based Parametric Painting
This addresses the challenge of generating aesthetically compelling and controlled paintings for artists or digital media applications, though it appears incremental as it builds on existing image-to-painting techniques.
The paper tackles the problem of creating large-scale, high-fidelity paintings from images by introducing a segmentation-based method with dynamic attention maps, resulting in outputs with human-like quality and stylistic variation that are functionally superior to previous methods, as confirmed by evaluations.
We introduce a novel image-to-painting method that facilitates the creation of large-scale, high-fidelity paintings with human-like quality and stylistic variation. To process large images and gain control over the painting process, we introduce a segmentation-based painting process and a dynamic attention map approach inspired by human painting strategies, allowing optimization of brush strokes to proceed in batches over different image regions, thereby capturing both large-scale structure and fine details, while also allowing stylistic control over detail. Our optimized batch processing and patch-based loss framework enable efficient handling of large canvases, ensuring our painted outputs are both aesthetically compelling and functionally superior as compared to previous methods, as confirmed by rigorous evaluations. Code available at: https://github.com/manuelladron/semantic\_based\_painting.git