Tag Archives: image processing

Study of smoothing filters – Savitzky-Golay filters

Posted on November 3, 2021 by bartwronski

Last week I saw Daniel Holden tweeting about Savitzky-Golay filters and their properties (less smoothing than a Gaussian filter) and I got excited… because I have never heard of them before and it’s an opportunity to learn something. When I … Continue reading →

Posted in Code / Graphics | Tagged algorithms, digital signal processing, image processing, maths, python, signal processing | Leave a comment

Practical Gaussian filtering: Binomial filter and small sigma Gaussians

Posted on October 31, 2021 by bartwronski

Gaussian filters are the bread and butter of signal and image filtering. They are isotropic and radially symmetric, filter out high frequencies extremely well, and just look pleasant and smooth. In this post I will cover two of my favorite … Continue reading →

Posted in Code / Graphics | Tagged algorithms, digital signal processing, filtering, Gaussian, graphics, graphics programming, image processing, signal processing | 2 Comments

Processing aware image filtering: compensating for the upsampling

Posted on July 20, 2021 by bartwronski

This post summarizes some thoughts and experiments on “filtering aware image filtering” I’ve been doing for a while. The core idea is simple – if you have some “fixed” step at the end of the pipeline that you cannot control … Continue reading →

Posted in Code / Graphics | Tagged algorithms, digital signal processing, filtering, graphics, image processing, jax, postprocessing, signal processing | 5 Comments

Comparing images in frequency domain. “Spectral loss” – does it make sense?

Posted on July 6, 2021 by bartwronski

Recently, numerous academic papers in the machine learning / computer vision / image processing domains (re)introduce and discuss a “frequency loss function” or “spectral loss” – and while for many it makes sense and nicely improves achieved results, some of … Continue reading →

Posted in Code / Graphics | Tagged algorithms, image processing, linear algebra, machine learning, maths, neural networks | 3 Comments

Neural material (de)compression – data-driven nonlinear dimensionality reduction

Posted on May 30, 2021 by bartwronski

In this post I come back to something I didn’t expect coming back to – dimensionality reduction and compression for whole material texture sets (as opposed to single textures) – a significantly underexplored topic. In one of my past posts … Continue reading →

Posted in Code / Graphics | Tagged compression, graphics, graphics programming, image processing, linear algebra, machine learning, maths, neural networks, PBR, physically-based shading, textures | 5 Comments

Computing gradients on grids of pixels and voxels – forward, central, and… diagonal differences

Posted on February 28, 2021 by bartwronski

In this post, I will focus on gradients of image signals defined on grids in computer graphics and image processing. Specifically, gradients / derivatives of images, height fields, distance fields, when they are represented as discrete, uniform grids of pixels … Continue reading →

Posted in Code / Graphics | Tagged antialiasing, digital signal processing, graphics programming, image processing, signal processing, supersampling | 6 Comments

Bilinear down/upsampling, aligning pixel grids, and that infamous GPU half pixel offset

Posted on February 15, 2021 by bartwronski

It’s been more than two decades of me using bilinear texture filtering, a few months since I’ve written about bilinear resampling, but only two days since I discovered a bug of mine related to it. 😅 Similarly, just last week … Continue reading →

Posted in Code / Graphics | Tagged digital signal processing, gpu, image processing, libraries, numpy, sampling, signal processing, upsampling | 9 Comments

Compressing PBR material texture sets with sparsity and k-SVD dictionary learning

Posted on August 30, 2020 by bartwronski

Introduction In this blog post, I am going to continue exploration of compressing whole PBR texture sets together (as opposed to compressing each texture from the set separately) and using the fact that those textures are strongly correlated. In my … Continue reading →

Posted in Code / Graphics | Tagged compression, graphics, graphics programming, image processing, linear algebra, machine learning, maths, PBR, rendering, signal processing, textures | 6 Comments

Dimensionality reduction for image and texture set compression

Posted on May 21, 2020 by bartwronski

In this blog post I am going to describe some of my past investigations on reducing the number of channels in textures / texture sets automatically and generally – without assuming anything about texture contents other than correspondence to some … Continue reading →

Posted in Code / Graphics | Tagged compression, graphics, image processing, linear algebra, machine learning, maths, PBR, physically-based shading, textures | 11 Comments

“Optimizing” blue noise dithering – backpropagation through Fourier transform and sorting

Posted on April 26, 2020 by bartwronski

Introduction This will be a blog post that is second in an (unanticipated) series on interesting uses of the JAX numpy autodifferentiation library, as well as an extra post in my very old post series on dithering in games and … Continue reading →

Posted in Code / Graphics | Tagged blue noise, dithering, frequency domain, image processing, jax, machine learning, noise, numpy, python | 4 Comments

Bilinear texture filtering – artifacts, alternatives, and frequency domain analysis

Posted on April 14, 2020 by bartwronski

In this post we will look at one of the staples of real-time computer graphics – bilinear texture filtering. To catch your interest, I will start with focusing on something that is often referred to as “bilinear artifacts”, trapezoid/star-shaped artifact … Continue reading →

Posted in Code / Graphics | Tagged blur, filtering, image processing, postprocessing, temporal, temporal supersampling | 11 Comments

Using JAX, numpy, and optimization techniques to improve separable image filters

Posted on March 15, 2020 by bartwronski

In today’s blog post I will look at two topics: how to use JAX (“hyped” new Python ML / autodifferentiation library), and a basic application that is follow-up to my previous blog post on using SVD for low-rank approximations and … Continue reading →

Posted in Code / Graphics | Tagged bokeh, colab, github, graphics programming, image processing, jax, machine learning, maths, numpy, postprocessing, programming, python | 9 Comments

Separate your filters! Separability, SVD and low-rank approximation of 2D image processing filters

Posted on February 3, 2020 by bartwronski

In this blog post, I explore separable convolutional image filters: how can we check if a 2D filter is separable, and how to compute separable approximations to any arbitrary 2D filter represented in a numerical / matrix form using SVD. Continue reading →

Posted in Code / Graphics | Tagged algorithms, approximation, blur, bokeh, depth of field, graphics, image processing, linear algebra, numpy, optimizations, postprocessing, python | 9 Comments

Local linear models and guided filtering – an alternative to bilateral filter

Posted on September 22, 2019 by bartwronski

Intro In this blog post I am going to describe an alternative tool for the graphics and image processing programmers’ toolbox – guided filtering. Guided filtering is a really handy tool that I learned about from my coworkers, and I … Continue reading →

Posted in Code / Graphics | Tagged bilateral, graphics, image processing, machine learning, postprocessing, python, signal processing, ssao, upsampling | 4 Comments