Author Archives: bartwronski

Gradient-descent optimized recursive filters for deconvolution / deblurring

Posted on September 5, 2022 by bartwronski

This post is a follow-up to my post on deconvolution/deblurring of the images. In my previous blog post, I discussed the process of “deconvolution” – undoing a known convolution operation. I have focused on traditional convolution filters – “linear phase, … Continue reading →

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

Progressive image stippling and greedy blue noise importance sampling

Posted on August 31, 2022 by bartwronski

Introduction I recently read the “Gaussian Blue Noise” paper by Ahmed et al. and was very impressed by the quality of their results and the rigor of their method. They provide a theoretical framework to analyze the quality of blue … Continue reading →

Posted in Code / Graphics | Tagged algorithms, blue noise, dithering, graphics, graphics programming, image processing, jax, programming, python, sampling | 3 Comments

Removing blur from images – deconvolution and using optimized simple filters

Posted on May 26, 2022 by bartwronski

In this post, we’ll have a look at the idea of removing blur from images, videos, or games through a process called “deconvolution”. We will analyze what makes the process of deblurring an image (blurred with a known blur kernel) … Continue reading →

Posted in Code / Graphics | 5 Comments

Transforming “noise” and random variables through non-linearities

Posted on March 16, 2022 by bartwronski

This post covers a topic slightly different from my usual ones and something I haven’t written much about before – applied elements of probability theory. We will discuss what happens with “noise” – a random variable – when we apply … Continue reading →

Posted in Code / Graphics | Tagged blue noise, graphics, graphics programming, image processing, jax, mathematics, maths, noise, programming, python | Leave a comment

Fast, GPU friendly, antialiasing downsampling filter

Posted on March 7, 2022 by bartwronski

In this shorter post, I will describe a 2X downsampling filter that I propose as a “safe default” for GPU image processing. It’s been an omission on my side that I have not proposed any specific filter despite writing so … Continue reading →

Posted in Code / Graphics | Tagged filtering, graphics, graphics programming, image processing, jax, postprocessing, signal processing | 6 Comments

Exposure Fusion – local tonemapping for real-time rendering

Posted on February 28, 2022 by bartwronski

In this post I want to close the loop and come back to the topic I described ~6y ago! Local tonemapping (I’ll refer to it as LTM) – a component I considered a missing piece in video games rendering, especially … Continue reading →

Posted in Code / Graphics | Tagged bilateral, graphics, graphics programming, image processing, postprocessing, tonemapping | Leave a comment

Light transport matrices, SVD, spectral analysis, and matrix completion

Posted on February 15, 2022 by bartwronski

In this post I’ll describe a small hike into the landscape of using linear algebra methods for analyzing seemingly non-algebraic problems, like light transport. This is very common in some domains of computer science / electrical engineering (seeing everything as … Continue reading →

Posted in Code / Graphics | Tagged image based lighting, linear algebra, mathematics | 1 Comment

Insider guide to tech interviews

Posted on January 4, 2022 by bartwronski

I’ve been meaning to write this post for over a year… an unofficial insider guide to tech interviews! This is the essence of the advice I give my friends (minus personal circumstances and preferences) all the time, and I figured … Continue reading →

Posted in Code / Graphics | 6 Comments

Procedural Kernel (Neural) Networks

Posted on January 3, 2022 by bartwronski

Last year I worked for a bit on a fun research project that ended up published as an arXiv “pre-print” / technical report and here comes a few paragraph “normal language” description of this work. Neural Networks are taking over … Continue reading →

Posted in Code / Graphics | Tagged image processing, linear algebra, machine learning, maths, signal processing | Leave a comment

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 | 5 Comments

Modding Korg MS-20 Mini – PWM, Sync, Osc2 FM

Posted on October 14, 2021 by bartwronski

Almost every graphics programmer I know is playing right now with some electronics (virtual high five!), so I won’t be any different. But I decided to make it “practical” and write something that might be useful to others – how … Continue reading →

Posted in Audio / Music / DSP | Tagged analog gear, electronics, korg, ms20, music, synthesizers, synths | 4 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 | 7 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 | 6 Comments

On leaving California and the Silicon Valley

Posted on June 28, 2021 by bartwronski

Beginning of the year, my wife and I made a final call – to leave California, “as soon as possible”. To be fair, we talked about this for a long time; a few years, but without any concrete date or … Continue reading →

Posted in Travel / Photography | 11 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

Superfast void-and-cluster Blue Noise in Python (Numpy/Jax)

Posted on April 21, 2021 by bartwronski

This is a super short blog post to accompany this Colab notebook. It’s not an official part of my dithering / Blue Noise post series, but thematically fits it well and be sure to check it out for some motivation … Continue reading →

Posted in Code / Graphics | Tagged blue noise, dithering, graphics programming, jax, numpy, python | 3 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 | 8 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 | 11 Comments

Is this a branch?

Posted on January 18, 2021 by bartwronski

Let’s try a new format – “shorts”; small blog posts where I elaborate on ideas that I’d discuss at my twitter, but they either come back over and over, or the short form doesn’t convey all the nuances. I often … Continue reading →

Posted in Code / Graphics | Tagged assembly, cpu, gpu, optimizations, profiling, programming, simd | 7 Comments