Cora: Correspondence-aware image editing using few step diffusion
Amirhossein Alimohammadi, Aryan Mikaeili, Sauradip Nag, Negar Hassanpour, Andrea Tagliasacchi, Ali Mahdavi-Amiri
摘要
Fig. 1.Cora supports diverse edits, including object insertion, subject and background changes, and non-rigid deformations (e.g., jumping).Our novel correspondence-aware method provides strong control and flexibility for both appearance and structure editing.Image editing is an important task in computer graphics, vision, and VFX, with recent diffusion-based methods achieving fast and high-quality results.However, edits requiring significant structural changes, such as non-rigid deformations, object modifications, or content generation, remain challenging.Existing few step editing approaches produce artifacts such as irrelevant texture or struggle to preserve key attributes of the source image (e.g., pose).
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 Paper2
- Interp3D: Correspondence-aware Interpolation for Generative Textured 3D MorphingXiaolu Liu, Yicong Li, Qiyuan He, Jiayin Zhu 等ICLR 2026 · 被引用 6 次
- Semantic-Structural Alignment for Generative Pictorial ChartsZhida Sun, Yulin Zhang, Zheng Gu, Min Lu 等SIGGRAPH 2026
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
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 被引用 11,724 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
- DragonDiffusion: Enabling Drag-style Manipulation on Diffusion ModelsChong Mou, Xintao Wang, Jiechong Song, Ying Shan 等ICLR 2024 · 被引用 223 次
- PAIR Diffusion: A Comprehensive Multimodal Object-Level Image EditorVidit Goel, Elia Peruzzo, Yifan Jiang, Dejia Xu 等CVPR 2024
- LooseRoPE: Content-aware Attention Manipulation for Semantic HarmonizationEtai Sella, Yoav Baron, Hadar Averbuch-Elor, Daniel Cohen-Or 等SIGGRAPH 2026
- Stable Flow: Vital Layers for Training-Free Image EditingOmri Avrahami, Or Patashnik, Ohad Fried, Egor Nemchinov 等CVPR 2025
- General Articulated Objects Manipulation in Real Images via Part-Aware Diffusion ProcessZhou Fang, Yong-Lu Li, Lixin Yang, Cewu LuNeurIPS 2024
