SemanticPaint: Interactive 3D Labelling and Learning at your Fingertips
57 641
58
Microsoft Research320 тыс
Следующее
10.07.15 – 14 3861:10Популярные
Опубликовано 30 июня 2015, 21:41
We present a new interactive approach to 3D scene understanding. Our system, SemanticPaint, allows users to simultaneously scan their environment, whilst interactively segmenting the scene simply by reaching out and touching any desired object or surface. Our system continuously learns from these segmentations, and labels new unseen parts of the environment. Unlike offline systems, where capture, labelling and batch learning often takes hours or even days to perform, our approach is fully online.
Read the paper:
research.microsoft.com/en-US/p...
Main Contacts:
Shahram Izadi, Microsoft Research: shahrami@microsoft.com
Interactive 3D Technologies, Microsoft Research:
research.microsoft.com/en-us/g...
Philip Torr, University of Oxford: philip.torr@eng.ox.ac.uk
Torr Vision Group, University of Oxford:
robots.ox.ac.uk/~tvg
Read the paper:
research.microsoft.com/en-US/p...
Main Contacts:
Shahram Izadi, Microsoft Research: shahrami@microsoft.com
Interactive 3D Technologies, Microsoft Research:
research.microsoft.com/en-us/g...
Philip Torr, University of Oxford: philip.torr@eng.ox.ac.uk
Torr Vision Group, University of Oxford:
robots.ox.ac.uk/~tvg
Свежие видео
12 дней – 2 5940:33
12 дней – 1 6370:24
13 дней – 1 4033:03
14 дней – 10810:25
14 дней – 2428:50Случайные видео
106 дней – 34 4070:15
178 дней – 257 41616:32
216 дней – 9 130 43024:42
348 дней – 3 2260:29
17.03.22 – 105 91912:42
06.05.14 – 8 1735:15
5 дней – 4 8080:20
7 дней – 11 05619:29
8 дней – 4 5114:52
8 дней – 5021:16
13 дней – 76 44621:37
14 дней – 1 0801:50