Papers › LMSCNet: Lightweight Multiscale 3D Semantic Completion
LMSCNet: Lightweight Multiscale 3D Semantic Completion
Luis Roldão, Raoul de Charette, Anne Verroust-Blondet
We introduce a new approach for multiscale 3Dsemantic scene completion from voxelized sparse 3D LiDAR scans. As opposed to the literature, we use a 2D UNet backbone with comprehensive multiscale skip connections to enhance feature flow, along with 3D segmentation heads. On the SemanticKITTI benchmark, our method performs on par on semantic completion and better on occupancy completion than all other published methods -- while being significantly lighter and faster. As such it provides a great performance/speed trade-off for mobile-robotics applications. The ablation studies demonstrate our method is robust to lower density inputs, and that it enables very high speed semantic completion at the coarsest level. Our code is available at https://github.com/cv-rits/LMSCNet.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Semantic Scene Completion | KITTI-360 | LMSCNet | mIoU | 13.65 | #4 of 7 | Archive leaderboard | report |
| 3D Semantic Scene Completion | NYUv2 | LMSCNet-SS | mIoU | 28.4 | #22 of 28 | Archive leaderboard | report |
| 3D Semantic Scene Completion | SemanticKITTI | LMSCNet-SS | mIoU | 17.6 | #9 of 20 | Archive leaderboard | report |
| 3D Semantic Scene Completion | SemanticKITTI | LMSCNet | mIoU | 17 | #12 of 20 | Archive leaderboard | report |
| 3D Semantic Scene Completion from a single RGB image | NYUv2 | LMSCNet (rgb input - reported in MonoScene paper) | mIoU | 15.88 | #6 of 6 | Archive leaderboard | report |
| 3D Semantic Scene Completion from a single RGB image | SemanticKITTI | LMSCNet (rgb input - reported in MonoScene paper) | mIoU | 7.09 | #8 of 9 | 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.
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