SketchGPT: Autoregressive Modeling for Sketch Generation and Recognition
This addresses sketch generation and recognition for applications like digital art or design tools, but it appears incremental as it builds on existing autoregressive modeling approaches.
The authors tackled the problem of generating and recognizing sketches by developing SketchGPT, an autoregressive sequence-to-sequence model that maps sketches to simplified primitive sequences, resulting in competitive performance with both qualitative and quantitative comparisons against state-of-the-art methods.
We present SketchGPT, a flexible framework that employs a sequence-to-sequence autoregressive model for sketch generation, and completion, and an interpretation case study for sketch recognition. By mapping complex sketches into simplified sequences of abstract primitives, our approach significantly streamlines the input for autoregressive modeling. SketchGPT leverages the next token prediction objective strategy to understand sketch patterns, facilitating the creation and completion of drawings and also categorizing them accurately. This proposed sketch representation strategy aids in overcoming existing challenges of autoregressive modeling for continuous stroke data, enabling smoother model training and competitive performance. Our findings exhibit SketchGPT's capability to generate a diverse variety of drawings by adding both qualitative and quantitative comparisons with existing state-of-the-art, along with a comprehensive human evaluation study. The code and pretrained models will be released on our official GitHub.