Develop Reference

Saving a pytoch tensor as a 32-bit grayscale Image

I have manipulated a 32-bit grayscale .tif image which I converted to tensor using PIL. After this I saved it with:
torchvision.utils.save_image(train_img_poac,fp=str(j)+".tif")
This method automatically converts the tensor to an RGB format image. I want my output image to be a 32-bit grayscale image.
I tried to use the arguments in the save_image function but could not find anything. Is converting it to numpy ndarray and then converting it to a 32-bit Image an option?

Unfortunately save_image doesn't have an option for preserving one-channel images. You can use a different library like OpenCV:
import cv2
image = train_img_poac.numpy()
cv2.imwrite('image_name', image)

How to deal with negative pixel values in images loaded using simpleITK

I have been working on DICOM CT scan images. I used simleITK to read the images to a numpy array. But the image pixel values are negative float values as shown in the image and the dtype of each pixel is float32. How to convert this pixel values to be able to train a TensorFlow 3D CNN model?
# Read the .nii image containing the volume with SimpleITK:
sitk_obj = sitk.ReadImage(filename)
# and access the numpy array:
image = sitk.GetArrayFromImage(sitk_obj)
negative pixel values
negative pixel values
The images read are of different shapes, how can I resize them to a specific constant image shapes?(as shown in below image)
different image shapes

If you use SimpleITK's RescaleIntensity function, you can rescale the pixel values to whatever range you require. Here's the docs for that function:
https://simpleitk.org/doxygen/latest/html/namespaceitk_1_1simple.html#af34ebbd0c41ae0d0a7a152ac1382bac6
To resize your images you can use SimpleITK's ResampleImageFilter. Here's the docs for that class:
https://simpleitk.org/doxygen/latest/html/classitk_1_1simple_1_1ResampleImageFilter.html
The following StackOverflow answer shows how to create a reference image that you resample your image onto:
https://stackoverflow.com/a/48065819/3712577
And this Github Gist how to resample several images to the same reference image:
https://gist.github.com/zivy/79d7ee0490faee1156c1277a78e4a4c4
Note that SimpleITK considers images as objects in physical space. So if the image origins, directions, and pixel spacings do not match up, then you will not get the result you expect.

Flat a point cloud (ply) to RGB image

I am trying to convert a ply to a RGB Image.
I can extract pcd.colors and pcd.points from the file, but how I can flat it to an RGB image.
np.asarray(pcd.colors)
np.asarray(pcd.points)
My problem is the above function give me a (1250459,3) array and I have to convert it to (X,Y,3) array, But what are X and Y? (image size)
I am using Open3D library in python to read ply data and have access to colors or points.

Convert grayscale png to RGB png image

I have a dataset of medical images in grayscale Png format which must be converted to RGB format. Tried many solutions but in vain.

GIMP, Menu image -> Mode -> RGB mode

If you want to just convert the format, the following method will help you:
In python3, using PILLOW and Numpy:
From PIL import Image
import numpy as np
im = Image.open(path/to/image, 'r').convert('L')
im = np.stack((im,)*3, axis=-1)
im = Image.fromarray(im)
im.save(path/to/save)
But if you want to colorize the image, know that colorization is an well-known image translation problem. Even if multiple approachs exist depending on the domain, I don't know any method that colorize any kind of images.
Some ways of doing so is to train a neural network, but for that, you need to have a dataset of B/W and colored images. Here are some approaches:
Using CNNs and considering the colorization as a regression problem: Let there be Color!
Using CNNs and considering the colorization as a classification problem: Colorful Image Colorization
Using GANs : cycle-gan

Blur Image using a Binary Mask - OpenCV Python

I have an RGB image and a binary mask of same dimensions. I want to blur only those portions of the RGB image where the value of mask is 255 (white). How to do this in OpenCV Python?
I tried implementing the method given in the answer of morotspaj in Smoothing Mat of float with mask but didn't quite get the result I was expecting. Can someone explain it?