Point-level ambiguity from local label disagreement is used to shrink contrastive margins, even to negative values, and this improves 3D semantic segmentation on S3DIS and ScanNet.
GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Point clouds captured by different sensors such as RGB-D cameras and LiDAR possess non-negligible domain gaps. Most existing methods design different network architectures and train separately on point clouds from various sensors. Typically, point-based methods achieve outstanding performances on even-distributed dense point clouds from RGB-D cameras, while voxel-based methods are more efficient for large-range sparse LiDAR point clouds. In this paper, we propose geometry-to-voxel auxiliary learning to enable voxel representations to access point-level geometric information, which supports better generalisation of the voxel-based backbone with additional interpretations of multi-sensor point clouds. Specifically, we construct hierarchical geometry pools generated by a voxel-guided dynamic point network, which efficiently provide auxiliary fine-grained geometric information adapted to different stages of voxel features. We conduct experiments on joint multi-sensor datasets to demonstrate the effectiveness of GeoAuxNet. Enjoying elaborate geometric information, our method outperforms other models collectively trained on multi-sensor datasets, and achieve competitive results with the-state-of-art experts on each single dataset.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentation
Point-level ambiguity from local label disagreement is used to shrink contrastive margins, even to negative values, and this improves 3D semantic segmentation on S3DIS and ScanNet.