![]() Furthermore, the vector representation for a given design is not unique, so models that supervise on the vector representation are unnecessarily constrained. This is not ideal because large-scale high quality vector-graphics datasets are difficult to obtain. ![]() ![]() The current alternative is to use specialized models that require explicit supervision on the vector graphics representation at training time. One can always rasterize the input graphic and resort to image-based generative approaches, but this negates the advantages of the vector representation. But, while a vast body of work has focused on generative algorithms for raster images, only a handful of options exists for vector graphics. Vector graphics are widely used to represent fonts, logos, digital artworks, and graphic designs. We envision that our generative model can facilitate efficient and intuitive clipart designs for novice users and graphic designers. To validate the proposed approach, we conducted several experiments and demonstrated its ability to vectorize and synthesize various clipart categories. We also introduced a collection of man-made object clipart, ClipNet, which is composed of closed-path layers, and two designed preprocessing tasks to clean up and enrich the original raw clipart. We formulated a joint loss function for training our generative model, including the shape similarity, symmetry, and local curve smoothness losses, as well as vector graphics rendering accuracy loss for synthesizing clipart recognizable by humans. The proposed approach is based on an iterative generative model that (i) decides whether to continue synthesizing a new layer and (ii) determines the geometry and appearance of the new layer. The final result is obtained by compositing all layers together into a vector clipart image that falls into the target category. Given a raster clipart image and its corresponding object category (e.g., airplanes), the proposed method sequentially generates new layers, each of which is composed of a new closed path filled with a single color. This paper presents a novel deep learning-based approach for automatically vectorizing and synthesizing the clipart of man-made objects. We reduce pixel aliasing artifacts and improve smoothness by fitting spline curves to contours in the image and optimizing their control points. This enables us to reshape the pixel cells so that neighboring pixels belonging to the same feature are connected through edges, thereby preserving the feature connectivity under magnification. The key to our algorithm is in resolving these ambiguities. ![]() This causes thin features to become visually disconnected under magnification by conventional means, and creates ambiguities in the connectedness and separation of diagonal neighbors. In the original image, pixels are represented on a square pixel lattice, where diagonal neighbors are only connected through a single point. Our algorithm resolves pixel-scale features in the input and converts them into regions with smoothly varying shading that are crisply separated by piecewise-smooth contour curves. We describe a novel algorithm for extracting a resolution-independent vector representation from pixel art images, which enables magnifying the results by an arbitrary amount without image degradation.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |