Fourier Feature Networks and Neural Volume Rendering
4 870
7.1
Microsoft Research334 тыс
Следующее
04.01.22 – 26843:19Популярные
67 дней – 1 12648:11
18.07.23 – 2 4284:44Опубликовано 3 января 2022, 16:35
Fourier Feature Networks are an exciting new development in Computer Vision, and their use for modeling radiance fields has produced a range of impressive results at the meeting point of Computer Vision and Computer Graphics. In this lecture, Matthew covers the motivation behind using Fourier features in neural network training, introduces the fundamentals of volumetric ray casting, and then shows how we can use Fourier Feature Networks to render high-quality novel views of complex 3D scenes.
This guest lecture was part of University of Cambridge Engineering Tripos Part IIB, 4F12: Computer Vision.
Speaker: Matthew Johnson, Research Software Engineer Lead at Microsoft Research, Cambridge
microsoft.com/en-us/research/p...
Access code and a Jupyter notebook for use in further learning at the companion Github repository: github.com/matajoh/fourier_fea...
This guest lecture was part of University of Cambridge Engineering Tripos Part IIB, 4F12: Computer Vision.
Speaker: Matthew Johnson, Research Software Engineer Lead at Microsoft Research, Cambridge
microsoft.com/en-us/research/p...
Access code and a Jupyter notebook for use in further learning at the companion Github repository: github.com/matajoh/fourier_fea...
Свежие видео
2 дня – 62253:30
3 дня – 028:25
4 дня – 47 58315:27
5 дней – 4 37643:51
5 дней – 17 4022:36
6 дней – 1 6161:01Случайные видео
16 дней – 28814:56
71 день – 376 95926:12
210 дней – 13 9910:52
22.04.23 – 5 0791:48
16.03.23 – 11531:42
09.11.21 – 5 56012:54
15 часов – 16432:15
1 день – 116 5961:00
2 дня – 455 1262:18:21
2 дня – 9581:30
3 дня – 019:31
5 дней – 1 9701:22
9 дней – 7310:32
