Photo-Sketching: Inferring Contour Drawings from Images
This work addresses the challenge of creating artistic contour drawings from images for applications in computer graphics and vision, offering a scalable alternative to boundary annotation that is easier for annotators.
The paper tackles the problem of generating contour drawings from images by addressing the mismatch between boundary detection outputs and artistic contour drawings, and introduces a new dataset and learning-based method that resolves annotation diversity and alignment issues. The method surpasses previous approaches quantitatively and qualitatively, and when fine-tuned on BSDS500, achieves state-of-the-art performance in salient boundary detection.
Edges, boundaries and contours are important subjects of study in both computer graphics and computer vision. On one hand, they are the 2D elements that convey 3D shapes, on the other hand, they are indicative of occlusion events and thus separation of objects or semantic concepts. In this paper, we aim to generate contour drawings, boundary-like drawings that capture the outline of the visual scene. Prior art often cast this problem as boundary detection. However, the set of visual cues presented in the boundary detection output are different from the ones in contour drawings, and also the artistic style is ignored. We address these issues by collecting a new dataset of contour drawings and proposing a learning-based method that resolves diversity in the annotation and, unlike boundary detectors, can work with imperfect alignment of the annotation and the actual ground truth. Our method surpasses previous methods quantitatively and qualitatively. Surprisingly, when our model fine-tunes on BSDS500, we achieve the state-of-the-art performance in salient boundary detection, suggesting contour drawing might be a scalable alternative to boundary annotation, which at the same time is easier and more interesting for annotators to draw.