Skip to main content
OverflowAI is here! AI power for your Stack Overflow for Teams knowledge community. Learn more

Questions tagged [upsampling]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
20 views

Quantization Parameters when converting Quantized Transposed Convolution to Conv2D

A simple way to compute TransposedConv2d is to convert it to a regular Conv2d by padding the input value with zeros, as is described in A guide to convolution arithmetic for deep learning. Does this ...
Necrotos's user avatar
1 vote
0 answers
65 views

Can a convolution learn to generate fine details? [closed]

I'm trying to get a convolutional autoencoder to reconstruct images of a dataset with crisp details. I've read in a couple places that convolutional autoencoders "naturally produce blurry images&...
Soltius's user avatar
  • 271
0 votes
0 answers
24 views

Given the high resolution signal and the low pass filter (kaiser filter), is there a way to reconstruct the low resolution signal?

When we upsampling a discrete 1d signal by 2x, we first interleave the signal by 0, then pass through a low pass filter. low resolution signal [x1, x2, x3, x4] -> interleave 0 -> [x1, 0, x2, 0, ...
Zongze Wu's user avatar
  • 101
0 votes
1 answer
69 views

What is the role of the word sampling in upsampling and downsampling?

Upsampling and downsampling are highly used in deep learning algorithms that involve convolutional neural networks. Upsampling increases the size downsampling decreases the size of tensors. What is ...
hanugm's user avatar
  • 3,880
2 votes
1 answer
921 views

Where can I read about upsampling methods in detail?

In deep learning, we encounter the upsample blocks several times, especially when we deal with images. Consider the following statements from description regarding UPSAMPLE in PyTorch The algorithms ...
hanugm's user avatar
  • 3,880
2 votes
1 answer
324 views

What does 'downsampling' and 'upsampling' mean in coarse-to-fine segmentation?

The paper here in section 2.1 Coarse-to-fine prediction: To increase the field of view presented to the CNN and reduce the redundancy among neighboring voxels, each image is downsampled by a factor ...
banikr's user avatar
  • 21