Diffusion model image completion method based on boundary perception

By introducing a boundary-aware convolutional module and a skip connection mechanism, the diffusion model structure is optimized, solving the problems of boundary discontinuity and structural distortion in image completion, achieving high-quality image completion results, and applicable to various image datasets such as natural scenes and faces.

CN121073818APending Publication Date: 2025-12-05GUILIN UNIV OF ELECTRONIC TECH
0 Cites 1 Cited by

Patent Information

Application Number
CN202511308578.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-15
Publication Date
2025-12-05

AI Technical Summary

Technical Problem

Existing diffusion probability models suffer from problems such as boundary discontinuity, structural distortion, and insufficient utilization of local information in image completion. In particular, when processing large missing areas, edge breakage and blurred transition are severe, leading to distorted completion results.

Method used

We introduce a boundary-aware convolutional module and a skip connection mechanism, combine them with a gradient decay mask, optimize the diffusion model structure, enhance boundary consistency and transition naturalness through a region adaptive scheduling strategy, and use boundary gradient maps and distance decay maps to model boundary information and dynamically adjust the information transmission intensity.

Benefits of technology

It significantly improves the structural consistency and detail fidelity of image completion, avoids edge blurring and misalignment, improves computational efficiency, and is suitable for a variety of image datasets.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a diffusion model image completion method based on boundary preserving perception, and belongs to the technical field of artificial intelligence and image generation. The method comprises the following steps: firstly, preprocessing an input image and a corresponding defect mask, and extracting gradient attenuation boundary features and a structure edge graph; a boundary sensing convolution module is introduced into the completion model and is used for boundary information modeling of a coding end; meanwhile, a gating mechanism is adopted in U-Net jump connection, the weight of a gradient attenuation mask is combined, and the boundary information transmission intensity is dynamically adjusted; furthermore, in the diffusion generation process, a region self-adaptive scheduling strategy is adopted, only high-step diffusion iteration is carried out on a defect region and a boundary neighborhood, and low-step or freezing operation is carried out on a non-defect region, so that balance between boundary consistency and calculation efficiency is realized. Experimental results show that the method is superior to an existing diffusion model image completion method in the aspects of structure retentivity, edge continuity and visual quality, and has wide application prospects.
Need to check novelty before this filing date? Find Prior Art