Semantic Scale Space: A Framework for Controllable Image Abstraction
Kazu Mishiba
Abstract
a) AGSS Abstraction Stages (Color) (b) XDoG on AGSS Abstraction Stages Figure 1. Controlling the abstraction of an input image is key to achieving high-quality stylized results. Our proposed method, AGSS, provides this control at the input level. (a) AGSS applied to a natural photograph: the original image (left) is progressively abstracted to weak (middle) and strong (right) levels, suppressing texture while preserving key structures. (b) XDoG line art applied with fixed parameters to each stage in (a): using the raw photograph as input (left) produces a cluttered result, whereas feeding in weak and strong AGSS bases (middle and right) yields cleaner, more iconic depictions whose level of simplification can be chosen by the user.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 98f55bdd-7cf8-42e0-af00-bcde01981be7Builds on4
- MuGE: Multiple Granularity Edge DetectionCaixia Zhou, Yaping Huang, Mengyang Pu, Qingji Guan et al.CVPR 2024 · 25 citations
- Sketch Generation with Drawing Process Guided by Vector Flow and GrayscaleZhengyan Tong, Xuanhong Chen, Bingbing Ni, Xiaohang WangAAAI 2021 · 24 citations
- Deep Flexible Structure Preserving Image SmoothingMingjia Li, Yuanbin Fu, Xinhui Li, Xiaojie GuoACM MM 2022 · 14 citations
- Learning to Cartoonize Using White-Box Cartoon RepresentationsXinrui Wang, Jinze YuCVPR 2020
Related papers
- Abstraction in Style: Beyond Texture and ColorMin Lu, Yuanfeng He, Anthony Chen, Jianhuang He et al.SIGGRAPH 2026
- CLIPascene: Scene Sketching with Different Types and Levels of AbstractionYael Vinker, Yuval Alaluf, Daniel Cohen-Or, Ariel ShamirICCV 2023 · 93 citations
- One-Shot Structure-Aware Stylized Image SynthesisHansam Cho, Jonghyun Lee, Seunggyu Chang, Yonghyun JeongCVPR 2024
- Interactive Cartoonization with Controllable Perceptual FactorsNamhyuk Ahn, Patrick Kwon, Jihye Back, Kibeom Hong et al.CVPR 2023
- Layered Image Vectorization via Semantic SimplificationZhenyu Wang, Jianxi Huang, Zhida Sun, Yuanhao Gong et al.CVPR 2025
