Search papers, labs, and topics across Lattice.
The paper introduces "Progressive Semantic Illusions," a vector sketching task where a single sketch evolves semantically through sequential stroke additions. To address the challenge of satisfying distinct semantic interpretations at different drawing stages, the authors propose "Stroke of Surprise," a generative framework using a dual-branch Score Distillation Sampling (SDS) mechanism for sequence-aware joint optimization. The method dynamically adjusts prefix strokes to find a common structural subspace and employs a novel Overlay Loss to enforce spatial complementarity, achieving superior performance in recognizability and illusion strength compared to baselines.
Imagine a single vector sketch that morphs from a duck into a sheep with each added stroke – this paper shows how to generate such mind-bending "progressive semantic illusions."
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 method dynamically adjusts prefix strokes to discover a"common structural subspace"valid for both targets. Furthermore, we introduce a novel Overlay Loss that enforces spatial complementarity, ensuring structural integration rather than occlusion. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines in recognizability and illusion strength, successfully expanding visual anagrams from the spatial to the temporal dimension. Project page: https://stroke-of-surprise.github.io/
