Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation

TL;DR

This paper introduces a semantics-aware, order-invariant graph-based method for sketch representation that links patches based on their semantic similarity, improving sketch synthesis and healing.

Contribution

It proposes a novel, learnable, semantics-aware graph construction method for sketch patches that enhances robustness and accuracy in sketch representation tasks.

Findings

Significant improvement in sketch synthesis quality.

Enhanced performance in sketch healing tasks.

Robust patch embeddings through message passing and clustering.

Abstract

Graphic sketch representations are effective for representing sketches. Existing methods take the patches cropped from sketches as the graph nodes, and construct the edges based on sketch's drawing order or Euclidean distances on the canvas. However, the drawing order of a sketch may not be unique, while the patches from semantically related parts of a sketch may be far away from each other on the canvas. In this paper, we propose an order-invariant, semantics-aware method for graphic sketch representations. The cropped sketch patches are linked according to their global semantics or local geometric shapes, namely the synonymous proximity, by computing the cosine similarity between the captured patch embeddings. Such constructed edges are learnable to adapt to the variation of sketch drawings, which enable the message passing among synonymous patches. Aggregating the messages from synonymous patches by graph convolutional networks plays a role of denoising, which is beneficial to produce robust patch embeddings and accurate sketch representations. Furthermore, we enforce a clustering constraint over the embeddings jointly with the network learning. The synonymous patches are self-organized as compact clusters, and their embeddings are guided to move towards their assigned cluster centroids. It raises the accuracy of the computed synonymous proximity. Experimental results show that our method significantly improves the performance on both controllable sketch synthesis and sketch healing.