Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910819840688128 |
|---|---|
| author | Sun, Shoukun Xian, Min Yao, Tiankai Xu, Fei Capriotti, Luca |
| author_facet | Sun, Shoukun Xian, Min Yao, Tiankai Xu, Fei Capriotti, Luca |
| contents | Producing large images using small diffusion models is gaining increasing popularity, as the cost of training large models could be prohibitive. A common approach involves jointly generating a series of overlapped image patches and obtaining large images by merging adjacent patches. However, results from existing methods often exhibit noticeable artifacts, e.g., seams and inconsistent objects and styles. To address the issues, we proposed Guided Fusion (GF), which mitigates the negative impact from distant image regions by applying a weighted average to the overlapping regions. Moreover, we proposed Variance-Corrected Fusion (VCF), which corrects data variance at post-averaging, generating more accurate fusion for the Denoising Diffusion Probabilistic Model. Furthermore, we proposed a one-shot Style Alignment (SA), which generates a coherent style for large images by adjusting the initial input noise without adding extra computational burden. Extensive experiments demonstrated that the proposed fusion methods improved the quality of the generated image significantly. The proposed method can be widely applied as a plug-and-play module to enhance other fusion-based methods for large image generation. Code: https://github.com/TitorX/GVCFDiffusion |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12771 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image Generation Sun, Shoukun Xian, Min Yao, Tiankai Xu, Fei Capriotti, Luca Computer Vision and Pattern Recognition Artificial Intelligence Producing large images using small diffusion models is gaining increasing popularity, as the cost of training large models could be prohibitive. A common approach involves jointly generating a series of overlapped image patches and obtaining large images by merging adjacent patches. However, results from existing methods often exhibit noticeable artifacts, e.g., seams and inconsistent objects and styles. To address the issues, we proposed Guided Fusion (GF), which mitigates the negative impact from distant image regions by applying a weighted average to the overlapping regions. Moreover, we proposed Variance-Corrected Fusion (VCF), which corrects data variance at post-averaging, generating more accurate fusion for the Denoising Diffusion Probabilistic Model. Furthermore, we proposed a one-shot Style Alignment (SA), which generates a coherent style for large images by adjusting the initial input noise without adding extra computational burden. Extensive experiments demonstrated that the proposed fusion methods improved the quality of the generated image significantly. The proposed method can be widely applied as a plug-and-play module to enhance other fusion-based methods for large image generation. Code: https://github.com/TitorX/GVCFDiffusion |
| title | Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2412.12771 |