插画师深度：用于图像分解的单目图层索引预测
Illustrator's Depth: Monocular Layer Index Prediction for Image Decomposition
提出一种新的深度定义——插画师深度，为每个像素预测图层索引，实现可编辑的图像分解；该表示可直接用于图像矢量化、文本到矢量图形生成、2D 到 3D 浮雕生成以及深度感知编辑，为视觉研究提供了可复用的分层表示思路。
原文依据 illustrator's depth infers a layer index for each pixel, forming an interpretable image decomposition through a discrete, globally consistent ordering of elements optimized for editability.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们引入了插画师深度，一种新颖的深度定义，旨在解决数字内容创作中的一个关键挑战：将平面图像分解为可编辑的、有序的图层。受艺术家构图过程的启发，插画师深度为每个像素推断一个图层索引，通过离散的、全局一致的元素排序形成可解释的图像分解，并针对可编辑性进行优化。我们还提出并训练了一个神经网络，使用精心策划的分层矢量图形数据集，直接从栅格输入预测分层。我们的图层索引推断解锁了一系列强大的下游应用。特别是，它在图像矢量化方面显著优于最优基线，同时还支持高保真文本到矢量图形生成、从2D图像自动生成3D浮雕以及直观的深度感知编辑。通过将深度从物理量重新定义为创意抽象，插画师深度预测为可编辑图像分解提供了新的基础。
英文原文摘要 1042 字符
We introduce Illustrator's Depth, a novel definition of depth that addresses a key challenge in digital content creation: decomposing flat images into editable, ordered layers. Inspired by an artist's compositional process, illustrator's depth infers a layer index for each pixel, forming an interpretable image decomposition through a discrete, globally consistent ordering of elements optimized for editability. We also propose and train a neural network using a curated dataset of layered vector graphics to predict layering directly from raster inputs. Our layer index inference unlocks a range of powerful downstream applications. In particular, it significantly outperforms state-of-the-art baselines for image vectorization while also enabling high-fidelity text-to-vector-graphics generation, automatic 3D relief generation from 2D images, and intuitive depth-aware editing. By reframing depth from a physical quantity to a creative abstraction, illustrator's depth prediction offers a new foundation for editable image decomposition.