TL;DR
This paper introduces a new vector sketching task called Progressive Semantic Illusions, where sketches evolve to depict different concepts through sequential strokes, and proposes a generative framework to optimize strokes for dual semantic constraints.
Contribution
The work presents a novel dual-constraint optimization framework for creating sketches that transform semantically over time, including a new Overlay Loss for structural integration.
Findings
Our method outperforms state-of-the-art baselines in recognizability.
It successfully creates sketches that evoke different concepts at different stages.
The approach expands visual illusions from spatial to temporal dimensions.
Abstract
Visual illusions traditionally rely on spatial manipulations such as multi-view consistency. In this work, we introduce Progressive Semantic Illusions, a novel vector sketching task where a single sketch undergoes a dramatic semantic transformation through the sequential addition of strokes. We present Stroke of Surprise, a generative framework that optimizes vector strokes to satisfy distinct semantic interpretations at different drawing stages. The core challenge lies in the "dual-constraint": initial prefix strokes must form a coherent object (e.g., a duck) while simultaneously serving as the structural foundation for a second concept (e.g., a sheep) upon adding delta strokes. To address this, we propose a sequence-aware joint optimization framework driven by a dual-branch Score Distillation Sampling (SDS) mechanism. Unlike sequential approaches that freeze the initial state, our…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Topics3D Shape Modeling and Analysis · Generative Adversarial Networks and Image Synthesis · Interactive and Immersive Displays
