Image vectorization and editing via linear gradient layer decomposition
Zheng-Jun Du, Liang-Fu Kang, Jianchao Tan, Yotam I. Gingold, Kun Xu
摘要
Fig. 1. Given the input image (1st column) and a segmentation mask (2nd column), we can decompose the image into several linear gradient layers to be saved in vector graphics (3rd column). Then we can perform recoloring (4th column) or object remove-insert-replace edits using these linear gradient layers in illustrator software (5th column). Image designed by Altagracia Art on Shutterstock.com.
A key advantage of vector graphics over raster graphics is their editability. For example, linear gradients define a spatially varying color fill with a few intuitive parameters, which are ubiquitously supported in standard vector graphics formats and libraries. By layering regions filled with linear gradients, complex appearances can be created. We propose an automatic method to convert a raster image into layered regions of linear gradients. Given an input raster image segmented into regions, our approach decomposes the resulting regions into opaque and semi-transparent linear gradient fills. Our approach is fully automatic (e.g., users do not identify a background as in previous approaches) and exhaustively considers all possible decompositions that satisfy perceptual cues. Experiments on a variety of images demonstrate that our method is robust and effective.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper16
- Transparent Image Layer Diffusion using Latent TransparencyLvmin Zhang, Maneesh AgrawalaSIGGRAPH 2024 · 被引用 42 次
- Deep Sketch Vectorization via Implicit Surface ExtractionChuan Yan, Yong Li, Deepali Aneja, Matthew Fisher 等SIGGRAPH 2024 · 被引用 12 次
- 3D-Layers: Bringing Layer-Based Color Editing to VR PaintingEmilie Yu, Fanny Chevalier, Karan Singh, Adrien BousseauSIGGRAPH 2024 · 被引用 11 次
- NeuralSVG: An Implicit Representation for Text-to-Vector GenerationSagi Polaczek, Yuval Alaluf, Elad Richardson, Yael Vinker 等ICCV 2025 · 被引用 6 次
- NIVeL: Neural Implicit Vector Layers for Text-to-Vector GenerationVikas Thamizharasan, Difan Liu, Matthew Fisher, Nanxuan Zhao 等CVPR 2024 · 被引用 5 次
它引用的顶会 Paper3
- PolyFit: perception-aligned vectorization of raster clip-art via intermediate polygonal fittingEdoardo Alberto Dominici, Nico Schertler, Jonathan Griffin, Shayan Hoshyari 等SIGGRAPH 2020 · 被引用 37 次
- Video recoloring via spatial-temporal geometric palettesZheng-Jun Du, Kai-Xiang Lei, Kun Xu, Jianchao Tan 等SIGGRAPH 2021 · 被引用 21 次
- Im2Vec: Synthesizing Vector Graphics Without Vector SupervisionPradyumna Reddy, Michaël Gharbi, Michal Lukác, Niloy J. MitraCVPR 2021
相关 Paper
- LayerD: Decomposing Raster Graphic Designs into LayersTomoyuki Suzuki, Kang-Jun Liu, Naoto Inoue, Kota YamaguchiICCV 2025 · 被引用 3 次
- Illustrator's Depth: Monocular Layer Index Prediction for Image DecompositionNissim Maruani, Peiying Zhang, Siddhartha Chaudhuri, Matthew Fisher 等CVPR 2026 · 被引用 1 次
- Generative Image Layer Decomposition with Visual EffectsJinrui Yang, Qing Liu, Yijun Li, Soo Ye Kim 等CVPR 2025
- ShapeAR: Generating Editable Shape Layers via Autoregressive DiffusionSouymodip Chakraborty, Ankur Singh, Amit Vikram Singh, Vineet Batra 等CVPR 2026
- SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract IconsHaiyang Xu, Ronghuan Wu, Li-Yi Wei, Nanxuan Zhao 等CVPR 2026 · 被引用 1 次
