CVPR 2018: Learning to See in the Dark

推荐理由

Remarkable machine learning result for "producing astoundingly sharp photos in very low light

推荐isp · 原文2018年5月

说明

这是2018年由Chen Chen发布的一部演示，主题归在Computer vision, speech & NLP。它讲的是low-light image enhancement这一支里的具体问题，而不是把整个领域扫一遍。适合已经能看懂基本术语、想继续往下走的人。内容上可以概括成：A short video accompanying the CVPR 2018 paper Learning to See in the Dark. It shows a neural network producing sharp images from very low-light raw sensor data, compared against denoising approaches.这些读者给出的理由，核心是：HN commenters flag it as a remarkable machine-learning result, notably for showing that training on raw images beats JPEG.它贴着当时的技术，看的时候要记得那是那个年份的判断。从2018年到2020年，有1位不同的读者在1个不同月份把它推荐出来，其中明确叫别人去看的有0次。适合先看结果再决定要不要深挖的人。先看它做成了什么。如果已经会了基本定义，就把注意力放在它怎么把low-light image enhancement变成能跟着复述的例子。

视频信息

频道

Chen Chen

时长

3 分 31 秒

发布年份

2018

同主题更多

• Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
• "Voice Driven Development: Who needs a keyboard anyway?" by Emily Shea
• Andrej Karpathy - AI for Full-Self Driving at Tesla
• Tensorflow and deep learning - without a PhD by Martin Görner
• JPEG DCT, Discrete Cosine Transform (JPEG Pt2)- Computerphile
• Fourier Optics used for Optical Pattern Recognition