Papers › MuGNet: Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation
MuGNet: Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation
Liuyue Xie, Tomotake Furuhata, Kenji Shimada
In this paper, we propose a multi-resolution deep-learning architecture to semantically segment dense large-scale pointclouds. Dense pointcloud data require a computationally expensive feature encoding process before semantic segmentation. Previous work has used different approaches to drastically downsample from the original pointcloud so common computing hardware can be utilized. While these approaches can relieve the computation burden to some extent, they are still limited in their processing capability for multiple scans. We present MuGNet, a memory-efficient, end-to-end graph neural network framework to perform semantic segmentation on large-scale pointclouds. We reduce the computation demand by utilizing a graph neural network on the preformed pointcloud graphs and retain the precision of the segmentation with a bidirectional network that fuses feature embedding at different resolutions. Our framework has been validated on benchmark datasets including Stanford Large-Scale 3D Indoor Spaces Dataset(S3DIS) and Virtual KITTI Dataset. We demonstrate that our framework can process up to 45 room scans at once on a single 11 GB GPU while still surpassing other graph-based solutions for segmentation on S3DIS with an 88.5% (+3%) overall accuracy and 69.8% (+7.7%) mIOU accuracy.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semantic Segmentation | S3DIS | MuGNet | Mean IoU | 69.8 | #26 of 54 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS | MuGNet | Number of params | N/A | #26 of 54 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS | MuGNet | oAcc | 88.5 | #26 of 54 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS Area5 | MuG-Net | Number of params | N/A | #48 of 61 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS Area5 | MuG-Net | mIoU | 63.5 | #48 of 61 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS Area5 | MuG-Net | oAcc | 88.1 | #48 of 61 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections