DemoCaricature: Democratising Caricature Generation with a Rough Sketch
Dar-Yen Chen, Ayan Kumar Bhunia, Subhadeep Koley, Aneeshan Sain, Pinaki Nath Chowdhury, Yi-Zhe Song
摘要
In this paper, we democratise caricature generation, empowering individuals to effortlessly craft personalised caricatures with just a photo and a conceptual sketch. Our objective is to strike a delicate balance between abstraction and identity, while preserving the creativity and subjectivity inherent in a sketch. To achieve this, we present Explicit Rank-1 Model Editing alongside single-image personalisation, selectively applying nuanced edits to cross-attention layers for a seamless merge of identity and style. Additionally, we propose Random Mask Reconstruction to enhance robustness, directing the model to focus on distinctive identity and style features. Crucially, our aim is not to replace artists but to eliminate accessibility barriers, allowing enthusiasts to engage in the artistry.
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 Paper8
- HarmonyCut: Supporting Creative Chinese Paper-cutting Design with Form and Connotation HarmonyHuanchen Wang, Tianrun Qiu, Jiaping Li, Zhicong Lu 等CHI 2025 · 被引用 17 次
- S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single SketchZidu Wang, Xiangyu Zhu, Jiang Yu, Tianshuo Zhang 等ACM MM 2024 · 被引用 3 次
- DynamicID: Zero-Shot Multi-ID Image Personalization With Flexible Facial EditabilityXirui Hu, Jiahao Wang, Hao Chen, Weizhan Zhang 等ICCV 2025 · 被引用 3 次
- CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature SynthesisDongyu Wang, Dar-Yen Chen, Yi-Zhe SongCVPR 2026
- Text-to-Image Diffusion Models are Great Sketch-Photo MatchmakersSubhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury 等CVPR 2024
它引用的顶会 Paper35
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 被引用 18,833 次
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 被引用 13,211 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
相关 Paper
- CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo BoothZhiyu Qu, Yunqi Miao, Zhensong Zhang, Jifei Song 等CVPR 2025
- CariPainter: Sketch Guided Interactive Caricature GenerationXin Huang, Dong Liang, Hongrui Cai, Juyong Zhang 等ACM MM 2022 · 被引用 5 次
- StyleCariGAN: caricature generation via StyleGAN feature map modulationWonjong Jang, Gwangjin Ju, Yucheol Jung, Jiaolong Yang 等SIGGRAPH 2021 · 被引用 51 次
- Controllable Face Sketch-Photo Synthesis with Flexible Generative PriorsKun Cheng, Mingrui Zhu, Nannan Wang, Guozhang Li 等ACM MM 2023 · 被引用 5 次
- Modeling Caricature Expressions by 3D Blendshape and Dynamic TextureKeyu Chen, Jianmin Zheng, Jianfei Cai, Juyong ZhangACM MM 2020 · 被引用 8 次
