arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15813cs.CVcs.LG
收藏

PixelTransformer:样本条件信号生成

PixelTransformer: Sample Conditioned Signal Generation

Facebook AI Research(Facebook人工智能研究院);Carnegie Mellon University(卡内基梅隆大学)

Shubham Tulsiani, Abhinav Gupta

摘要:

我们提出了一种生成模型,可以推断出稀疏样本条件下的潜在空间信号的分布,例如,给出几个观察到的像素的似是而非的图像。与序列自回归生成模型相比,我们的模型允许对任意样本进行调节,并且可以回答任何位置的分布查询。我们在三个图像数据集上经验性地验证了我们的方法,并表明我们学会了生成多样化和有意义的样本,并且在观察到更多像素的情况下,分布方差减小。我们还表明,我们的方法适用于图像之外,并且可以生成其他类型的空间输出,例如多项式,3D形状和视频。

英文摘要:

We propose a generative model that can infer a distribution for the underlying spatial signal conditioned on sparse samples e.g. plausible images given a few observed pixels. In contrast to sequential autoregressive generative models, our model allows conditioning on arbitrary samples and can answer distributional queries for any location. We empirically validate our approach across three image datasets and show that we learn to generate diverse and meaningful samples, with the distribution variance reducing given more observed pixels. We also show that our approach is applicable beyond images and can allow generating other types of spatial outputs e.g. polynomials, 3D shapes, and videos.

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。

↑