3-Sweep: Extracting Editable Objects from a Single Photo, SIGGRAPH ASIA 2013
推荐理由
this single video blew my mind back in *2013* and I find myself thinking about it often.
强烈推荐alfiedotwtf · 原文
说明
这是2013年由Daniel CohenOr发布的一部演示,主题归在Computer vision, speech & NLP。它讲的是single-image 3d reconstruction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 SIGGRAPH Asia 2013 research demo of 3-Sweep, a tool for extracting editable 3D objects from a single photo using a few user strokes. It predates modern AI image tools.这些读者给出的理由,核心是:HN recalls it as a mind-blowing pre-AI demo of 2D-to-3D object extraction.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2013年到2024年,有2位不同的读者在2个不同月份把它推荐出来,其中明确叫别人去看的有1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single-image 3d reconstruction变成能跟着复述的例子。
视频信息
- 频道
- Daniel CohenOr
- 时长
- 5 分 51 秒
- 发布年份
- 2013
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