Lossy Geometry Compression for High Resolution Voxel Scenes - Paper presentation

I got the opportunity to present my Master thesis research at the I3D conference on interactive 3D graphics and games. It was all virtual this year, so this is the recorded presentation that was played there live a few days ago.

Slides with notes: https://www.dropbox.com/s/tv1n022b7u3m5j7/Lossy%20SVDAG%20compression%20slides%20-%20I3D2020.pdf?dl=0

In the coming weeks I'm planning to upload more cool clips of the rendering/coding adventures I recorded along the way.

If you're interested, you can find my thesis and the paper submitted to the conference here; my thesis has a more detailed introduction to the subject, but the paper is a lot more polished:
https://repository.tudelft.nl/islandora/object/uuid%3A83057534-111d-43bc-84f3-67a6ffe1af3b?collection=education
https://graphics.tudelft.nl/Publications-new/2020/VSE20/LossyGeometryCompressionForHighResolutionVoxelScenes.pdf

The code can be found on my Github, though it might be hard to navigate as it quickly grew due to all of the experiments: https://github.com/RvanderLaan/SVDAG-Compression

Abstract:
Sparse Voxel Directed Acyclic Graphs (SVDAGs) losslessly compress highly detailed geometry in a high-resolution binary voxel grid by identifying matching elements. This representation is suitable for highperformance real-time applications, such as free-viewpoint videos and high-resolution precomputed shadows. In this work, we introduce a lossy scheme to further decrease memory consumption by minimally modifying the underlying voxel grid to increase matches. Our method efficiently identifies groups of similar but rare subtrees in an SVDAG structure and replaces them with a single common subtree representative. We test our compression strategy on several standard voxel datasets, where we obtain memory reductions of 10% up to 50% compared to a standard SVDAG, while introducing an error (ratio of modified voxels to voxel count) of only 1% to 5%. Furthermore, we show that our method is complementary to other state of the art SVDAG optimizations, and has a negligible effect on real-time rendering performance.

Contents:
0:00 Welcome
0:17 Introduction
1:54 Background
4:10 Our method
10:00 Results
13:00 Conclusions

Тэги:

#sparse_voxel_dag #dag #sparse_voxel_octree #ray_casting #compression #geometry #lossy #svdag #i3d #clustering #markov #markov_clustering #voxels

Скачать видео