<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Projects on Martin Bálint</title><link>https://balint.io/projects/</link><description>Recent content in Projects on Martin Bálint</description><generator>Hugo</generator><language>en</language><managingEditor>martin@balint.io (Martin Bálint)</managingEditor><webMaster>martin@balint.io (Martin Bálint)</webMaster><lastBuildDate>Sat, 01 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://balint.io/projects/index.xml" rel="self" type="application/rss+xml"/><item><title>Forget Superresolution, Sample Adaptively (when Path Tracing)</title><link/><pubDate>Sat, 01 Aug 2026 00:00:00 +0000</pubDate><author>martin@balint.io (Martin Bálint)</author><guid/><description>An end-to-end pipeline that learns where path-tracing samples matter, then reconstructs a detailed image from the sparse result.</description></item><item><title>Learning Neural Antiderivatives</title><link/><pubDate>Mon, 01 Sep 2025 00:00:00 +0000</pubDate><author>martin@balint.io (Martin Bálint)</author><guid/><description>A learning-based treatment of antiderivatives using neural representations.</description></item><item><title>Histogram Stratification for Spatio-Temporal Reservoir Sampling</title><link/><pubDate>Fri, 01 Aug 2025 00:00:00 +0000</pubDate><author>martin@balint.io (Martin Bálint)</author><guid/><description>A stratification method for improving spatiotemporal reservoir sampling.</description></item><item><title>Self-Supervised Video Defocus Deblurring with Atlas Learning</title><link/><pubDate>Thu, 01 Aug 2024 00:00:00 +0000</pubDate><author>martin@balint.io (Martin Bálint)</author><guid/><description>Self-supervised video defocus deblurring through an atlas-based representation.</description></item><item><title>Joint Sampling and Optimisation for Inverse Rendering</title><link/><pubDate>Fri, 01 Dec 2023 00:00:00 +0000</pubDate><author>martin@balint.io (Martin Bálint)</author><guid/><description>A method that treats sample allocation and stochastic optimization as one coupled inverse-rendering problem.</description></item><item><title>Neural Partitioning Pyramids for Denoising Monte Carlo Renderings</title><link/><pubDate>Tue, 01 Aug 2023 00:00:00 +0000</pubDate><author>martin@balint.io (Martin Bálint)</author><guid/><description>A learned pyramidal filter that reconstructs low-sample-count path-traced images while avoiding ringing and scale-composition artifacts.</description></item><item><title>Closed Form Transmittance in Heterogeneous Media Using Cosine Noise</title><link/><pubDate>Mon, 01 Apr 2019 00:00:00 +0000</pubDate><author>martin@balint.io (Martin Bálint)</author><guid/><description>Closed-form transmittance for heterogeneous media represented with cosine noise.</description></item></channel></rss>