I have hard time to find anything similar. Gephi comes to mind but it doesn't have interface as rich as in Obsidian for example. Any additional deep learning abilities would be great. Maybe any software, tools or libraries? 

Is there any tools similar to obsidian or roam but 1) with weight assignment on note connections with filters in visualization 2) 3d visualizing?

I am working on a super-resolution project. And for now, I am using Transposed Convolution for upsampling the image. But I have heard a lot that sub-pixel convolutions do it better. So what is subpixel convolution and the math behind it? And Why it is better than transposed convolution? 

Image convolution centers on interpolation.

Sub-pixel rendering is based on the fact that a pixel is composed of three color components, say R G B horizontally. A white pixel of width 2/3 on the border of a white area can be rendered in false color as R G. Especially font rendering is improved by sub-pixel rendering.

The geometry of the color components may vary, like B G R. A wrong geometry will destroy the intended extra sharpness. Also, note that the positive effect is on the x-axis.

Consider a Pixel #cccccc two-third width: for instance #ffff00. And a half-pixel #ff8800. More or less. Should weight the green component higher probably.

Sub-pixel convolution just operates with these sub-pixels, instead of just till pixel level. Your data model has for the x coordinate 3 times higher resolution and combines triples in a special way.

Grayscale images may exploit sub-pixel rendering best.

neural-network

Trending Blogposts on neural-network

Popular Discussions on neural-network

openIs there any tools similar to obsidian or roam but 1) with weight assignment on note connections with filters in visualization 2) 3d visualizing?

1

0

0

openWhat is sub-pixel convolution?

1

1

0

PRODUCTS

QUICK LINKS

LEGAL

neural-network

Trending Blogposts on neural-network

Popular Discussions on neural-network

openIs there any tools similar to obsidian or roam but 1) with weight assignment on note connections with filters in visualization 2) 3d visualizing?

1

0

0

openWhat is sub-pixel convolution?

1

1

0