{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T07:04:56Z","timestamp":1781334296019,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","funder":[{"name":"The Research Grants Council (RGC) of Hong Kong","award":["CityU 11216122"],"award-info":[{"award-number":["CityU 11216122"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763964","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9741-9876","authenticated-orcid":false,"given":"Ronghuan","family":"Wu","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7498-3033","authenticated-orcid":false,"given":"Wanchao","family":"Su","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-5377","authenticated-orcid":false,"given":"Jing","family":"Liao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.14430","author":"Avrahami Omri","year":"2024","unstructured":"Omri Avrahami, Or Patashnik, Ohad Fried, Egor Nemchinov, Kfir Aberman, Dani Lischinski, and Daniel Cohen-Or. 2024. Stable Flow: Vital Layers for Training-Free Image Editing. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.14430."},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1037210.1037238"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02149"},{"key":"e_1_3_3_2_8_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.14368","author":"Cheng Yutao","year":"2024","unstructured":"Yutao Cheng, Zhao Zhang, Maoke Yang, Hui Nie, Chunyuan Li, Xinglong Wu, and Jie Shao. 2024. Graphic Design with Large Multimodal Model. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.14368."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Laurent Demaret Nira Dyn and Armin Iske. 2006. Image Compression by Linear Splines over Adaptive Triangulations. Signal Processing 86 7 1604\u20131616.","DOI":"10.1016\/j.sigpro.2005.09.003"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"crossref","unstructured":"Edoardo\u00a0Alberto Dominici Nico Schertler Jonathan Griffin Shayan Hoshyari Leonid Sigal and Alla Sheffer. 2020. PolyFit: Perception-aligned Vectorization of Raster Clip-art via Intermediate Polygonal Fitting. ACM Transactions on Graphics 39 4 77\u20131.","DOI":"10.1145\/3386569.3392401"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Zhengjun Du Liangfu Kang Jianchao Tan Yotam Gingold and Kun Xu. 2023. Image Vectorization and Editing via Linear Gradient Layer Decomposition. ACM Transactions on Graphics 42 4 1\u201313.","DOI":"10.1145\/3592128"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3229147.3229155"},{"key":"e_1_3_3_2_14_1","volume-title":"International Conference on Machine Learning","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, Kyle Lacey, Alex Goodwin, Yannik Marek, and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In International Conference on Machine Learning."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Jean-Dominique Favreau Florent Lafarge and Adrien Bousseau. 2017. Photo2ClipArt: Image Abstraction and Vectorization Using Layered Linear Gradients. ACM Transactions on Graphics 36 6 1\u201311.","DOI":"10.1145\/3130800.3130888"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687922"},{"key":"e_1_3_3_2_17_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.04007","author":"Ge Yuying","year":"2024","unstructured":"Yuying Ge, Sijie Zhao, Chen Li, Yixiao Ge, and Ying Shan. 2024. SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.04007."},{"key":"e_1_3_3_2_18_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.01626","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-Prompt Image Editing with Cross Attention Control. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.01626."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27987"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Shayan Hoshyari Edoardo\u00a0Alberto Dominici Alla Sheffer Nathan Carr Zhaowen Wang Duygu Ceylan and I-Chao Shen. 2018. Perception-Driven Semi-Structured Boundary Vectorization. ACM Transactions on Graphics 37 4 1\u201314.","DOI":"10.1145\/3197517.3201312"},{"key":"e_1_3_3_2_21_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.09685","author":"Hu Edward\u00a0J.","year":"2021","unstructured":"Edward\u00a0J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.09685."},{"key":"e_1_3_3_2_22_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.17672","author":"Huang Ian","year":"2024","unstructured":"Ian Huang, Guandao Yang, and Leonidas Guibas. 2024. BlenderAlchemy: Editing 3D Graphics with Vision-Language Models. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.17672."},{"key":"e_1_3_3_2_23_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.14397","author":"Huang Shijie","year":"2025","unstructured":"Shijie Huang, Yiren Song, Yuxuan Zhang, Hailong Guo, Xueyin Wang, Mike\u00a0Zheng Shou, and Jiaming Liu. 2025. PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.14397."},{"key":"e_1_3_3_2_24_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.01506","author":"Ju Xuan","year":"2023","unstructured":"Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, and Qiang Xu. 2023. Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.01506."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964994"},{"key":"e_1_3_3_2_26_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.15228","author":"Kulits Peter","year":"2024","unstructured":"Peter Kulits, Haiwen Feng, Weiyang Liu, Victoria Abrevaya, and Michael\u00a0J. Black. 2024. Re-Thinking Inverse Graphics With Large Language Models. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.15228."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Ho Law and SungHa Kang. 2025. Image Vectorization with Depth: Convexified Shape Layers with Depth Ordering. SIAM Journal on Imaging Sciences 18 2 963\u20131001.","DOI":"10.1137\/24M1692551"},{"key":"e_1_3_3_2_28_1","first-page":"349","volume-title":"Eurographics Symposium on Rendering","author":"Lecot Gregory","year":"2006","unstructured":"Gregory Lecot and Bruno Levy. 2006. ARDECO: Automatic Region DEtection and Conversion. In Eurographics Symposium on Rendering. 349\u2013360."},{"key":"e_1_3_3_2_29_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.12058","author":"Lei Xuanyu","year":"2024","unstructured":"Xuanyu Lei, Zonghan Yang, Xinrui Chen, Peng Li, and Yang Liu. 2024. Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.12058."},{"key":"e_1_3_3_2_30_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.15649","author":"Li Senmao","year":"2023","unstructured":"Senmao Li, Joost Van De\u00a0Weijer, Taihang Hu, Fahad\u00a0Shahbaz Khan, Qibin Hou, Yaxing Wang, and Jian Yang. 2023. StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.15649."},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"crossref","unstructured":"Tzu-Mao Li Michal Luk\u00e1\u010d Gharbi Micha\u00ebl and Jonathan Ragan-Kelley. 2020. Differentiable Vector Graphics Rasterization for Editing and Learning. ACM Transactions on Graphics 39 6 1\u201315.","DOI":"10.1145\/3414685.3417871"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Zicheng Liao Hugues Hoppe David Forsyth and Yizhou Yu. 2012. A Subdivision-Based Representation for Vector Image Editing. IEEE Transactions on Visualization and Computer Graphics 18 11 1858\u20131867.","DOI":"10.1109\/TVCG.2012.76"},{"key":"e_1_3_3_2_33_1","first-page":"115712","volume-title":"Advances in Neural Information Processing Systems","author":"Lin Haonan","year":"2024","unstructured":"Haonan Lin, Yan Chen, Jiahao Wang, Wenbin An, Mengmeng Wang, Feng Tian, Yong Liu, Guang Dai, Jingdong Wang, and Qianying Wang. 2024. Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing. In Advances in Neural Information Processing Systems. 115712\u2013115756."},{"key":"e_1_3_3_2_34_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.07065","author":"Liu Vivian","year":"2024","unstructured":"Vivian Liu, Rubaiat\u00a0H. Kazi, Li-Yi Wei, Matthew Fisher, Timothy Langlois, Seth Walker, and Lydia Chilton. 2024. LogoMotion: Visually Grounded Code Generation for Content-Aware Animation. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.07065."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731209"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01583"},{"key":"e_1_3_3_2_37_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.01073","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.01073."},{"key":"e_1_3_3_2_38_1","first-page":"2063","volume-title":"IEEE Winter Conference on Applications of Computer Vision","author":"Miyake Daiki","year":"2025","unstructured":"Daiki Miyake, Akihiro Iohara, Yu Saito, and Toshiyuki Tanaka. 2025. Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models. In IEEE Winter Conference on Applications of Computer Vision. 2063\u20132072."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"crossref","unstructured":"Alexandrina Orzan Adrien Bousseau Holger Winnem\u00f6ller Pascal Barla Jo\u00eblle Thollot and David Salesin. 2008. Diffusion Curves: A Vector Representation for Smooth-Shaded Images. ACM Transactions on Graphics 27 3 1\u20138.","DOI":"10.1145\/1360612.1360691"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_2_42_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T. Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3D using 2D Diffusion. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14988."},{"key":"e_1_3_3_2_43_1","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong-Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_3_2_44_1","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter\u00a0J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research 21 140 1\u201367."},{"key":"e_1_3_3_2_45_1","first-page":"7342","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Reddy Pradyumna","year":"2021","unstructured":"Pradyumna Reddy, Michael Gharbi, Michal Lukac, and Niloy\u00a0J. Mitra. 2021. Im2Vec: Synthesizing Vector Graphics without Vector Supervision. In IEEE Conference on Computer Vision and Pattern Recognition. 7342\u20137351."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"crossref","unstructured":"I-Chao Shen and BingYu Chen. 2021. ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis. IEEE Transactions on Visualization and Computer Graphics 28 12 4211\u20134224.","DOI":"10.1109\/TVCG.2021.3084944"},{"key":"e_1_3_3_2_47_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-scale Image Recognition. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1409.1556."},{"key":"e_1_3_3_2_48_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01105","author":"Song Yiren","year":"2025","unstructured":"Yiren Song, Danze Chen, and Mike\u00a0Zheng Shou. 2025. LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01105."},{"key":"e_1_3_3_2_49_1","unstructured":"Hao Su Jianwei Niu Xuefeng Liu Jiahe Cui and Ji Wan. 2021. MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.04830."},{"key":"e_1_3_3_2_50_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.02193","author":"Sun Fan-Yun","year":"2024","unstructured":"Fan-Yun Sun, Weiyu Liu, Siyi Gu, Dylan Lim, Goutam Bhat, Federico Tombari, Manling Li, Nick Haber, and Jiajun Wu. 2024. LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.02193."},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"crossref","unstructured":"Jian Sun Lin Liang Fang Wen and Heung-Yeung Shum. 2007. Image Vectorization Using Optimized Gradient Meshes. ACM Transactions on Graphics 26 3 11\u2013es.","DOI":"10.1145\/1276377.1276391"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR.2006.30"},{"key":"e_1_3_3_2_53_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.07232","author":"Tewel Yoad","year":"2024","unstructured":"Yoad Tewel, Rinon Gal, Dvir Samuel, Yuval Atzmon, Lior Wolf, and Gal Chechik. 2024. Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.07232."},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00759"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Xingze Tian and Tobias G\u00fcnther. 2022. A Survey of Smooth Vector Graphics: Recent Advances in Representation Creation Rasterization and Image Vectorization. IEEE Transactions on Visualization and Computer Graphics 30 3 1652\u20131671.","DOI":"10.1109\/TVCG.2022.3220575"},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_3_2_57_1","unstructured":"Jiangshan Wang Junfu Pu Zhongang Qi Jiayi Guo Yue Ma Nisha Huang Yuxin Chen Xiu Li and Ying Shan. 2024b. Taming Rectified Flow for Inversion and Editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.04746."},{"key":"e_1_3_3_2_58_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.05404","author":"Wang Zhenyu","year":"2024","unstructured":"Zhenyu Wang, Jianxi Huang, Zhida Sun, Yuanhao Gong, Daniel Cohen-Or, and Min Lu. 2024a. Layered Image Vectorization via Semantic Simplification. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.05404."},{"key":"e_1_3_3_2_59_1","volume-title":"International Conference on Learning Representations","author":"Wei Cong","year":"2024","unstructured":"Cong Wei, Zheyang Xiong, Weiming Ren, Xeron Du, Ge Zhang, and Wenhu Chen. 2024. OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"crossref","unstructured":"Tian Xia Binbin Liao and Yizhou Yu. 2009. Patch-Based Image Vectorization with Automatic Curvilinear Feature Alignment. ACM Transactions on Graphics 28 5 1\u201310.","DOI":"10.1145\/1618452.1618461"},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"crossref","unstructured":"Guofu Xie Xin Sun Xin Tong and Derek Nowrouzezahrai. 2014. Hierarchical Diffusion Curves for Accurate Automatic Image Vectorization. ACM Transactions on Graphics 33 6 1\u201311.","DOI":"10.1145\/2661229.2661275"},{"key":"e_1_3_3_2_63_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.17323","author":"Xu Yingjing","year":"2024","unstructured":"Yingjing Xu, Jie Kong, Jiazhi Wang, Xiao Pan, Bo Lin, and Qiang Liu. 2024a. InsightEdit: Towards Better Instruction Following for Image Editing. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.17323."},{"key":"e_1_3_3_2_64_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15034","author":"Xu Yu","year":"2024","unstructured":"Yu Xu, Fan Tang, Juan Cao, Yuxin Zhang, Xiaoyu Kong, Jintao Li, Oliver Deussen, and Tong-Yee Lee. 2024b. HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15034."},{"key":"e_1_3_3_2_65_1","doi-asserted-by":"crossref","unstructured":"Chuan Yan Yong Li Deepali Aneja Matthew Fisher Edgar Simo-Serra and Yotam Gingold. 2024. Deep Sketch Vectorization via Implicit Surface Extraction. ACM Transactions on Graphics 43 4 1\u201313.","DOI":"10.1145\/3658197"},{"key":"e_1_3_3_2_66_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.11441","author":"Yang Jianwei","year":"2023","unstructured":"Jianwei Yang, Hao Zhang, Feng Li, Xueyan Zou, Chunyuan Li, and Jianfeng Gao. 2023. Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.11441."},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"crossref","unstructured":"Ming Yang Hongyang Chao Chi Zhang Jun Guo Lu Yuan and Jian Sun. 2015. Effective Clipart Image Vectorization Through Direct Optimization of Bezigons. IEEE Transactions on Visualization and Computer Graphics 22 2 1063\u20131075.","DOI":"10.1109\/TVCG.2015.2440273"},{"key":"e_1_3_3_2_68_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.02884","author":"Yang Tao","year":"2024","unstructured":"Tao Yang, Yingmin Luo, Zhongang Qi, Yang Wu, Ying Shan, and Chang\u00a0Wen Chen. 2024. PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.02884."},{"key":"e_1_3_3_2_69_1","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15738","author":"Yu Qifan","year":"2024","unstructured":"Qifan Yu, Wei Chow, Zhongqi Yue, Kaihang Pan, Yang Wu, Xiaoyang Wan, Juncheng Li, Siliang Tang, Hanwang Zhang, and Yueting Zhuang. 2024. AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15738."},{"key":"e_1_3_3_2_70_1","unstructured":"Kai Zhang Lingbo Mo Wenhu Chen Huan Sun and Yu Su. 2023. MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing. Advances in Neural Information Processing Systems 31428\u201331449."},{"key":"e_1_3_3_2_71_1","doi-asserted-by":"crossref","unstructured":"Peiying Zhang Nanxuan Zhao and Jing Liao. 2024. Text-to-Vector Generation with Neural Path Representation. ACM Transactions on Graphics 43 4 1\u201313.","DOI":"10.1145\/3658204"},{"key":"e_1_3_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_73_1","doi-asserted-by":"crossref","unstructured":"Song-Hai Zhang Tao Chen Yi-Fei Zhang Shimin Hu and Ralph\u00a0Robert M.2009. Vectorizing Cartoon Animations. IEEE Transactions on Visualization and Computer Graphics 15 4 618\u2013629.","DOI":"10.1109\/TVCG.2009.9"},{"key":"e_1_3_3_2_74_1","doi-asserted-by":"crossref","unstructured":"Haozhe Zhao Xiaojian\u00a0Shawn Ma Liang Chen Shuzheng Si Rujie Wu Kaikai An Peiyu Yu Minjia Zhang Qing Li and Baobao Chang. 2024. UltraEdit: Instruction-based Fine-Grained Image Editing at Scale. Advances in Neural Information Processing Systems 37 3058\u20133093.","DOI":"10.52202\/079017-0100"},{"key":"e_1_3_3_2_75_1","doi-asserted-by":"crossref","unstructured":"Shuang Zhao Fr\u00e9do Durand and Changxi Zheng. 2017. Inverse Diffusion Curves using Shape Optimization. IEEE Transactions on Visualization and Computer Graphics 24 7 2153\u20132166.","DOI":"10.1109\/TVCG.2017.2721400"},{"key":"e_1_3_3_2_76_1","first-page":"165","volume-title":"European Conference on Computer Vision","author":"Zhou Hengyu","year":"2024","unstructured":"Hengyu Zhou, Hui Zhang, and Bin Wang. 2024. Segmentation-Guided Layer-Wise Image Vectorization with Gradient Fills. In European Conference on Computer Vision. 165\u2013180."}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:29:20Z","timestamp":1765250960000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763964"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":75,"alternative-id":["10.1145\/3757377.3763964","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763964","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}