It's All About Your Sketch: Democratising Sketch Control in Diffusion Models
Subhadeep Koley, Ayan Kumar Bhunia, Deeptanshu Sekhri, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song
2024年份
18顶会引用
摘要
Sketch ControlNet T2I-Adapter Ours Sketch ControlNet T2I-Adapter Ours Edgemap ControlNet T2I-Adapter Ours Our Results Figure 1. Top-left: Comparison of images generated by our method with SGDM [81], ControlNet [90], and T2I-Adapter [55]. Top-right: A set of photos generated by our method. Bottom: While existing methods [55, 90] generate realistic images from pixel-perfect edgemaps, they perform sub-optimally for freehand abstract sketches. (Best view when zoomed in.
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 Paper18
- AirSketch: Generative Motion to SketchHui Xian Grace Lim, Xuanming Cui, Yogesh S. Rawat, Ser Nam LimNeurIPS 2024 · 被引用 4 次
- SketchingReality: From Freehand Scene Sketches to Photorealistic ImagesAhmed Bourouis, Mikhail Bessmeltsev, Yulia GryaditskayaICLR 2026 · 被引用 3 次
- LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text PairingFederico Girella, Davide Talon, Ziyue Liu, Zanxi Ruan 等ICCV 2025 · 被引用 2 次
- Universal Multi-Domain Translation via Diffusion RoutersDuc Kieu, Kien Do, Tuan Hoang, Thao Minh Le 等ICLR 2026 · 被引用 2 次
- Component-Wise Sketching and Generation for Car Interior DesignJeongche Yoon, Seung-Jun Lee, Donghyeok Ma, Seok-Hyung BaeCHI 2026 · 被引用 1 次
它引用的顶会 Paper52
- 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
- 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
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li 等NeurIPS 2022 · 被引用 8,965 次
相关 Paper
- Picture that Sketch: Photorealistic Image Generation from Abstract SketchesSubhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury 等CVPR 2023
- Block and Detail: Scaffolding Sketch-to-Image GenerationVishnu Sarukkai, Lu Yuan, Mia Tang, Maneesh Agrawala 等UIST 2024 · 被引用 23 次
- SketchyCOCO: Image Generation From Freehand Scene SketchesChengying Gao, Qi Liu, Qi Xu, Limin Wang 等CVPR 2020
- DeFLOCNet: Deep Image Editing via Flexible Low-Level ControlsHongyu Liu, Ziyu Wan, Wei Huang, Yibing Song 等CVPR 2021
- Neural Contours: Learning to Draw Lines From 3D ShapesDifan Liu, Mohamed Nabail, Aaron Hertzmann, Evangelos KalogerakisCVPR 2020
