Structured grid layouts are preferable in many 2D visual content creation scenarios since their structures facilitate further layout editing. Multiple geometry-based methods can effectively create structured grid layouts but require user-provided constraints or rules. Existing data-driven approaches have achieved remarkable layout generation performance, but fail to produce appropriate layout structures. We present GTLayout, a novel generative model for structured grid layout generation. We adopt general trees to represent structured grid layouts and exploit a recursive neural network (RvNN) for this generation task. Our model can handle grid layouts with varied structures and regular arrangements. Qualitative and quantitative experiments on public grid layout datasets show that our method outperforms several baselines in the tasks of layout reconstruction and layout generation, especially for datasets containing few samples. We also demonstrate that the structured layout space constructed by our method can blend structures of layouts, as well as providing a visualization and analysis of the layout space. Additionally, we consider two application cases based on GTLayout: multiple layout interpolation and conditional layout generation. Our code is available at https://github.com/Warren-swr/GT-Layout.

With the rising ubiquity of digital touch devices and sketch-based interfaces, freehand sketching has become an essential mode of visual communication. Nevertheless, interpreting these often ambiguous and sparse sketches poses challenges for computers. This paper presents Sketchformer++, a hierarchical transformer architecture for the neural representation of vector sketches. It treats a vector sketch as a three-level structure, at sketch level, stroke level, and segment level. Three self-attention modules are adopted in the network architecture, corresponding to the sketch hierarchy. The semantics of sketches are aggregated from local to global levels, resulting in neural representations of sketches. Extensive experiments show that Sketchformer++ helps to achieve superior performance in various downstream tasks, including sketch reconstruction, sketch recog-nition, sketch semantic segmentation, and sketch retrieval, demonstrating its robustness and effectiveness as a means of sketch representation. Code is available at https://github.com/BHR7/SketchformerPlus.

We present a novel method to produce discernible image mosaics, with relatively large image tiles replaced by images drawn from a database, to resemble a target image. Compared to existing works on image mosaics, the novelty of our method is two-fold. Firstly, believing that the presence of visual edges in the final image mosaic strongly supports image perception, we develop an edge-aware photo retrieval scheme which emphasizes the preservation of visual edges in the target image. Secondly, unlike most previous works which apply a pre-determined partition to an input image, our image mosaics are composed of adaptive tiles, whose sizes are determined based on the available images in the database and the objective of maximizing resemblance to the target image. We show discernible image mosaics obtained by our method, using image collections of only moderate size. To evaluate our method, we conducted a user study to validate that the image mosaics generated present both globally and locally appropriate visual impressions to the human observers. Visual comparisons with existing techniques demonstrate the superiority of our method in terms of mosaic quality and perceptibility.