Lune

ICCV2025顶会

Progressive Artwork Outpainting Via Latent Diffusion Models

Dae-Young Song, Jung-Jae Yu, Donghyeon Cho

2025年份
2被引次数
1顶会引用

摘要

Figure 1. Outpainting comparisons between single-step (a) and progressive approaches (b,c). (a) Results of the single-step outpainting. We first resize the input image to a fixed size suitable for a conventional outpainting model, and then apply outpainting. After that, we revert the image to its original aspect ratio. Finally, we use a super-resolution model to restore the reduced resolution. (b) Results of progressive outpainting without consideration of overall composition. (c) Results of our method with global context consideration and planning. The red bounding boxes indicate the inputs.

Progressive approach enables outpainting in any direction and produces high-fidelity, high-resolution images with no restrictions on aspect ratio. Furthermore, our method produces globally harmonious outpainting results compared to models that do not take overall composition into account.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

引用它的顶会 Paper1

问问它们各自怎么用它

它引用的顶会 Paper30

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖