| Paper | Code | mIoU | ModelName | ReleaseDate |
|---|---|---|---|---|
| Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding | ✓ Link | 73.4 | Volt-B (extra data) | 2026-04-21 |
| DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation | ✓ Link | 73.3 | DITR (extra data) | 2025-03-24 |
| LitePT: Lighter Yet Stronger Point Transformer | ✓ Link | 73.1 | LitePT-S | 2025-12-15 |
| vFusedSeg3D: 3rd Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation | 72.46 | vFusedSeg3D | 2024-08-09 | |
| Multi-Space Alignments Towards Universal LiDAR Segmentation | ✓ Link | 72.4 | M3Net | 2024-05-02 |
| Image-to-Point Cloud Feature Back-Projection for Multimodal Training of 3D Semantic Segmentation | 72.4 | IPFP(PTv3) | 2026-06-03 | |
| Multi-Scale Neighborhood Occupancy Masked Autoencoder for Self-Supervised Learning in LiDAR Point Clouds | 72.3 | NOMAE | 2025-02-27 | |
| Point Transformer V3: Simpler, Faster, Stronger | ✓ Link | 72.1 | Point Transformer V3 + PPT (extra data) | 2023-12-15 |