Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation

2025-09-30

AI Summary

Existing noise-map inversion methods for text-guided image editing achieve high-fidelity source reconstruction but suffer from weak text alignment and limited editing flexibility. To address this, we propose an editable noise-map optimization framework: target images are inverted into an intermediate noise space of a diffusion model, and a joint objective simultaneously optimizes reconstruction fidelity and text-guided constraints while minimizing the discrepancy between source and edited noise maps—thereby significantly improving text alignment accuracy and semantic controllability. Furthermore, we introduce a temporal consistency constraint to extend the method to video editing. Our approach outperforms state-of-the-art methods on image editing benchmarks, preserving source content integrity while enhancing semantic adherence. Notably, it is the first to enable end-to-end, text-driven video editing via noise-map inversion.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Optimization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Text-to-image diffusion models have achieved remarkable success in generating high-quality and diverse images. Building on these advancements, diffusion models have also demonstrated exceptional performance in text-guided image editing. A key strategy for effective image editing involves inverting the source image into editable noise maps associated with the target image. However, previous inversion methods face challenges in adhering closely to the target text prompt. The limitation arises because inverted noise maps, while enabling faithful reconstruction of the source image, restrict the flexibility needed for desired edits. To overcome this issue, we propose Editable Noise Map Inversion (ENM Inversion), a novel inversion technique that searches for optimal noise maps to ensure both content preservation and editability. We analyze the properties of noise maps for enhanced editability. Based on this analysis, our method introduces an editable noise refinement that aligns with the desired edits by minimizing the difference between the reconstructed and edited noise maps. Extensive experiments demonstrate that ENM Inversion outperforms existing approaches across a wide range of image editing tasks in both preservation and edit fidelity with target prompts. Our approach can also be easily applied to video editing, enabling temporal consistency and content manipulation across frames.

Problem

• Overcoming noise map limitations in text-guided image editing fidelity
• Enhancing editability while preserving source image content integrity
• Improving target prompt adherence during diffusion-based image manipulation

Innovation

• Encodes target image into editable noise maps
• Refines noise for content preservation and editability
• Enables high-fidelity image and video manipulation