CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing

[2506.18438] CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2506.18438 (cs) [Submitted on 23 Jun 2025 ( v1 ), last revised 11 Jun 2026 (this version, v3)] Title: CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing Authors: Dinh-Khoi Vo , Thanh-Toan Do , Tam V. Nguyen , Minh-Triet Tran , Trung-Nghia Le View a PDF of the paper titled CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing, by Dinh-Khoi Vo and Thanh-Toan Do and Tam V. Nguyen and Minh-Triet Tran and Trung-Nghia Le View PDF HTML (experimental) Abstract: Editing natural images using textual descriptions in text-to-image diffusion models remains a significant challenge, particularly in achieving consistent generation and handling complex, non-rigid objects. Existing methods often struggle to preserve textures and identity, require extensive fine-tuning, and exhibit limitations in editing specific spatial regions or objects while retaining background details. This paper proposes Context-Preserving Adaptive Manipulation (CPAM), a novel zero-shot framework for complicated, non-rigid real image editing. Specifically, we propose a preservation adaptation module that adjusts self-attention mechanisms to preserve and independently control the object and background effectively. This ensures that the objects' shapes, textures, and identities are maintained while keeping the background undistorted during the editing process using the mask guidance technique. Additionally, we develop a localized extraction module to mitigate the interference with the non-desired modified regions during conditioning in cross-attention mechanisms. We also introduce various mask-guidance strategies to facilitate diverse image manipulation tasks in a simple manner. CPAM can be seamlessly integrated with multiple diffusion backbones, including SD1.5, SD2.1, and SDXL, demonstrating strong generalization across different model architectures. Extensive experiments on our newly constructed Image Manipulation BenchmArk (IMBA), a robust benchmark dataset specifically designed for real image editing, demonstrate that our proposed method is the preferred choice among human raters, outperforming existing state-of-the-art editing techniques. The source code and data will be publicly released at the project page: this https URL Comments: Accepted to IEEE Transactions on Multimedia. Project page: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2506.18438 [cs.CV] (or arXiv:2506.18438v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2506.18438 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Trung Nghia Le [ view email ] [v1] Mon, 23 Jun 2025 09:19:38 UTC (25,185 KB) [v2] Sat, 11 Apr 2026 17:10:20 UTC (34,460 KB) [v3] Thu, 11 Jun 2026 05:10:10 UTC (34,456 KB) Full-text links: Access Paper: View a PDF of the paper titled CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing, by Dinh-Khoi Vo and Thanh-Toan Do and Tam V. Nguyen and Minh-Triet Tran and Trung-Nghia Le View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration#609699
• How is effectuation effectual? The role of artifact decomposition in enabling non-predictive control#405883
• Light exposure and sleep architecture in real-world settings.#362086
• Learning Adaptive and Visually Aligned Conditions for Generative Zero-Shot Learning#1143700
• On image restoration via nonlinear anisotropic PDE with non-standards growth conditions.#1090787