MSc thesis presentation - Floria Gu

Name: Floria Gu

Date: September 11, 2025

Time: 10 am

Location: ICCS 104

Supervisor's name: Alla Sheffer

Title of thesis: TABI: Tight and Balanced Interactive Atlas Packing

Abstract:
Atlas packing algorithms seek to arrange a set of charts within a fixed-size atlas with as little downscaling as possible, and are a key step of many computer graphics applications. Many packing applications such as content creation tools, dynamic atlas generation in video games, and texture space shading require on-the-fly, interactive atlas packing. Unfortunately, while many methods have been developed for generating tight, high-quality packings, they are designed for {\em offline} settings and have running times two or more orders of magnitude greater than what is required for interactive performance. While real-time GPU packing methods exist, they significantly downscale the packed charts compared to offline methods. We introduce a GPU packing method that targets interactive speeds, provides packing quality approaching that of offline methods, and supports flexible user control over the tradeoff between performance and quality. We analyze the two main factors leading to poor performance of current real-time packing methods -- a lack of packing tightness and lack of balance -- and explicitly address them to significantly increase packing quality. Our method generates tight packings by compacting empty space between irregularly shaped charts both horizontally and vertically, using two approximations of chart shape that support efficient parallel processing. Our packings are more balanced as a result of a robust strategy that places charts into the atlas one row at a time, and selects the locally optimal placement of each row based on the current state of the packing. We show that our method significantly reduces chart downscaling compared to existing interactive methods while remaining orders of magnitude faster than offline alternatives.