RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification

[2503.02537] RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification 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:2503.02537 (cs) [Submitted on 4 Mar 2025 ( v1 ), last revised 9 Apr 2026 (this version, v4)] Title: RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification Authors: Zhen Yang , Guibao Shen , Minyang Li , Liang Hou , Mushui Liu , Luozhou Wang , Xin Tao , Ying-Cong Chen View a PDF of the paper titled RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification, by Zhen Yang and 7 other authors View PDF HTML (experimental) Abstract: Diffusion models have achieved remarkable progress across various visual generation tasks. However, their performance significantly declines when generating content at resolutions higher than those used during training. Although numerous methods have been proposed to enable high-resolution generation, they all suffer from inefficiency. In this paper, we propose RectifiedHR, a straightforward and efficient solution for training-free high-resolution synthesis. Specifically, we propose a noise refresh strategy that unlocks the model's training-free high-resolution synthesis capability and improves efficiency. Additionally, we are the first to observe the phenomenon of energy decay, which may cause image blurriness during the high-resolution synthesis process. To address this issue, we introduce average latent energy analysis and find that tuning the classifier-free guidance hyperparameter can significantly improve generation performance. Our method is entirely training-free and demonstrates efficient performance. Furthermore, we show that RectifiedHR is compatible with various diffusion model techniques, enabling advanced features such as image editing, customized generation, and video synthesis. Extensive comparisons with numerous baseline methods validate the superior effectiveness and efficiency of RectifiedHR. Comments: Project Page: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2503.02537 [cs.CV] (or arXiv:2503.02537v4 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2503.02537 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhen Yang [ view email ] [v1] Tue, 4 Mar 2025 12:03:26 UTC (45,473 KB) [v2] Fri, 14 Mar 2025 13:40:17 UTC (41,130 KB) [v3] Mon, 26 May 2025 14:37:27 UTC (38,094 KB) [v4] Thu, 9 Apr 2026 09:03:54 UTC (44,826 KB) Full-text links: Access Paper: View a PDF of the paper titled RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification, by Zhen Yang and 7 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-03 Change to browse by: cs cs.AI 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

• Finding the K best synthesis plans#632959
• Data Synthesis and Parameter-Efficient Fine-Tuning for Low-Resource NMT: A Case Study on Q'eqchi' Mayan#267640
• Judging to Improve: A De-biased VLM-as-3D-Judge Protocol for Single-Image 3D Generation#290589
• K-TRAIL: Simulator-Guided Generative Design of EM/RF Circuits#1048928
• Alternating Error Effects on Decomposition Method in Function Generation Synthesis#369375