# Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching

Source: [Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching](<https://www.sota2.com/research/paper/698eb05ec97a0b3e3b5e69a6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-20T05:00:05.687Z

Authors: Huai-Hsun Cheng, Siang-Ling Zhang, Yu-Lun Liu

Published: 2026-02-12T18:59:54.000Z

## 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 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/

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Progressive Illusion Sketch Generation on Object Dataset](<https://www.sota2.com/research/sota/progressive-illusion-sketch-generation-on-object-dataset.md>): Progressive Illusion Sketch Generation; Object Dataset; Phase 1 CLIP Avg: 30.044.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.12280>)

[PDF](<https://arxiv.org/pdf/2602.12280.pdf>)

[Implementation](<https://github.com/stroke-of-surprise/Stroke-Of-Surprise>)
