Generating Sketches in a Hierarchical Auto-Regressive Process for Flexible Sketch Drawing Manipulation at Stroke-Level
Sicong Zang, Shuhui Gao, Zhijun Fang

TL;DR
This paper introduces a hierarchical auto-regressive model for sketch generation that allows flexible, stroke-level manipulation during the drawing process by predicting, anchoring, and translating strokes in a three-stage hierarchy.
Contribution
It proposes a novel hierarchical auto-regressive approach enabling real-time, stroke-level manipulation during sketch generation, overcoming limitations of previous methods that require pre-collected conditions.
Findings
Allows flexible stroke-level manipulation during sketch generation
Produces more coherent and controllable sketches
Outperforms existing methods in sketch quality and flexibility
Abstract
Generating sketches with specific patterns as expected, i.e., manipulating sketches in a controllable way, is a popular task. Recent studies control sketch features at stroke-level by editing values of stroke embeddings as conditions. However, in order to provide generator a global view about what a sketch is going to be drawn, all these edited conditions should be collected and fed into generator simultaneously before generation starts, i.e., no further manipulation is allowed during sketch generating process. In order to realize sketch drawing manipulation more flexibly, we propose a hierarchical auto-regressive sketch generating process. Instead of generating an entire sketch at once, each stroke in a sketch is generated in a three-staged hierarchy: 1) predicting a stroke embedding to represent which stroke is going to be drawn, and 2) anchoring the predicted stroke on the canvas,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
