“He dabbled in some other open source machine learning things on Github. Seems pretty off the grid. Recently published this paper: https://arxiv.org/abs/1702.00783”
Pixel Recursive Super Resolution
We present a pixel recursive super resolution model that synthesizes realistic details into images while enhancing their resolution. A low resolution image may correspond to multiple plausible high resolution images, thus modeling the super resolution process with a pixel independent conditional model often results in averaging different details--hence blurry edges. By contrast, our model is able to represent a multimodal conditional distribution by properly modeling the statistical dependencies among the high resolution image pixels, conditioned on a low resolution input. We employ a PixelCNN architecture to define a strong prior over natural images and jointly optimize this prior with a deep conditioning convolutional network. Human evaluations indicate that samples from our proposed model look more photo realistic than a strong L2 regression baseline.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“2012: https://www.instantfundas.com/2012/10/how-to-unblur-out-of-focus-and-blurred.html 2017: https://arxiv.org/pdf/1702.00783.pdf (Pixel Recursive Super Resolution) 2020: https://venturebeat.com/2020/01/22/researchers-use-ai-to-deblur-human-faces-in-photos/ Edit: Most face recognition software works by down-sizing and blurring an image to faster detec…”
- Pixel Recursive Super Resolution ↗Tomte · 2017-02-03 · 19 分
- Pixel Recursive Super Resolution ↗somerandomness · 2017-02-06 · 107 分