https://github.com/trevor-m/tensorflow-bicubic-downsample

tf.image.resize_images has aliasing when downsampling and does not have gradients for bicubic mode. This implementation fixes those problems.
https://github.com/trevor-m/tensorflow-bicubic-downsample

aliasing bicubic deep-learning downsample gradients image-processing image-resizing images resize-images super-resolution tensorflow

Last synced: 27 days ago
JSON representation

tf.image.resize_images has aliasing when downsampling and does not have gradients for bicubic mode. This implementation fixes those problems.

• Host: GitHub
• URL: https://github.com/trevor-m/tensorflow-bicubic-downsample
• Owner: trevor-m
• License: mit
• Created: 2018-05-17T04:30:29.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2019-05-03T19:51:45.000Z (about 6 years ago)
• Last Synced: 2024-11-09T22:38:10.151Z (6 months ago)
• Topics: aliasing, bicubic, deep-learning, downsample, gradients, image-processing, image-resizing, images, resize-images, super-resolution, tensorflow
• Language: Python
• Size: 12.7 KB
• Stars: 24
• Watchers: 2
• Forks: 4
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# tensorflow-bicubic-downsample

tf.image.resize_images has aliasing when downsampling and does not define gradients for bicubic mode. This implementation fixes those problems.

# Example

These images have been downsampled by a factor of 4 from the original. The results from this code matches the scipy.misc.imresize results exactly.

Method | Result | Comments

--- | --- | ---

Original |  | This is the original full res image.

tf.images.resize_images |  | TF's implementation has aliasing

scipy.misc.imresize |  | Proper bicubic downsampling

This code |  | Matches scipy exactly

# Usage

```python

from bicubic_downsample import build_filter, apply_bicubic_downsample

# First, create the bicubic kernel. This can be reused in multiple downsample operations

k = build_filter(factor=4)

# Downsample x which is a tensor with shape [N, H, W, 3]

y = apply_bicubic_downsample(x, filter=k, factor=4)

# y now contains x downsampled to [N, H/4, W/4, 3]

```