超越现实：利用StickerNet学习表现性创作
Beyond Realism: Learning the Art of Expressive Composition with StickerNet
AI总结：
StickerNet通过学习真实世界编辑模式，实现了表现性图像合成，超越传统真实感追求，提升艺术性和用户意图的表达。
摘要：
作为图像编辑流程中广泛使用的操作，图像合成传统上专注于实现视觉真实性和语义合理性。然而，在现代内容创作景观中的实际编辑场景中，许多合成并非旨在保持真实性。相反，受平台用户追求社区认可的动机驱动，用户往往旨在创造更具艺术性、趣味性或社会吸引力的内容。受此观察的启发，我们定义了表现性合成任务，这是一种新的图像合成形式，它拥抱了风格多样性和松散的布局逻辑，反映了用户在现实世界创意平台上编辑图像的方式。为了解决这一尚未被充分探索的问题，我们提出了StickerNet，一个两阶段框架，首先确定合成类型，然后相应地预测诸如不透明度、掩码、位置和缩放等布局参数。与以往通过模拟对象在真实图像上的放置来构建数据集的工作不同，我们直接从一个匿名的在线视觉创作和编辑平台上收集了180万次编辑动作来构建数据集，每次都反映了用户-社区验证的放置决策。这种基于真实编辑行为的构建确保了任务定义和训练监督之间的强对齐。用户研究和定量评估表明，StickerNet优于常见的基线方法，并且与人类布局行为紧密匹配，证明了从真实世界编辑模式中学习的有效性，尽管任务本身存在内在的模糊性。这项工作引入了视觉理解的新方向，强调表现性和用户意图而非真实性。
英文摘要：
As a widely used operation in image editing workflows, image composition has traditionally been studied with a focus on achieving visual realism and semantic plausibility. However, in practical editing scenarios of the modern content creation landscape, many compositions are not intended to preserve realism. Instead, users of online platforms motivated by gaining community recognition often aim to create content that is more artistic, playful, or socially engaging. Taking inspiration from this observation, we define the expressive composition task, a new formulation of image composition that embraces stylistic diversity and looser placement logic, reflecting how users edit images on real-world creative platforms. To address this underexplored problem, we present StickerNet, a two-stage framework that first determines the composition type, then predicts placement parameters such as opacity, mask, location, and scale accordingly. Unlike prior work that constructs datasets by simulating object placements on real images, we directly build our dataset from 1.8 million editing actions collected on an anonymous online visual creation and editing platform, each reflecting user-community validated placement decisions. This grounding in authentic editing behavior ensures strong alignment between task definition and training supervision. User studies and quantitative evaluations show that StickerNet outperforms common baselines and closely matches human placement behavior, demonstrating the effectiveness of learning from real-world editing patterns despite the inherent ambiguity of the task. This work introduces a new direction in visual understanding that emphasizes expressiveness and user intent over realism.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
