arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.07370cs.CV
收藏

基于样本的随机匹配图像合成

Example-Based Image Synthesis via Randomized Patch-Matching

Technion – Israel Institute of Technology(以色列理工学院)

Yi Ren, Yaniv Romano, Michael Elad

摘要:

图像和纹理合成是图像处理、图形学和机器学习领域中一个具有挑战性的课题。这个问题包括通过训练样本或通过参数化建模来对所需类型的图像进行建模,然后生成属于相同统计原点的图像。这项工作解决了图像合成任务,重点是两个特定的家庭的图像-手写数字和人脸图像。本文提供了两个主要贡献。首先,我们提出了一个简单而直观的算法,能够以统一的方式生成这样的图像。所提出的方法是金字塔式的,包括放大和细化估计图像几次。对于每个放大阶段,该算法从补丁数据库中随机抽取小补丁,并合并这些补丁以形成具有高视觉质量的连贯且新颖的图像。第二个贡献是一个通用的框架,生成性能的评估,它结合了三个方面:合成图像的可能性,原创性和传播。我们评估了所提出的合成方案,并表明结果在性质上是相似的,但与训练集中发现的结果不同,这表明已经获得了真正的合成效果。

英文摘要:

Image and texture synthesis is a challenging task that has long been drawing attention in the fields of image processing, graphics, and machine learning. This problem consists of modelling the desired type of images, either through training examples or via a parametric modeling, and then generating images that belong to the same statistical origin. This work addresses the image synthesis task, focusing on two specific families of images -- handwritten digits and face images. This paper offers two main contributions. First, we suggest a simple and intuitive algorithm capable of generating such images in a unified way. The proposed approach taken is pyramidal, consisting of upscaling and refining the estimated image several times. For each upscaling stage, the algorithm randomly draws small patches from a patch database, and merges these to form a coherent and novel image with high visual quality. The second contribution is a general framework for the evaluation of the generation performance, which combines three aspects: the likelihood, the originality and the spread of the synthesized images. We assess the proposed synthesis scheme and show that the results are similar in nature, and yet different from the ones found in the training set, suggesting that true synthesis effect has been obtained.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑