Unsupervised Point Cloud Registration via Training-Time Semantic Guidance

• URL: http://arxiv.org/abs/2609.15228v1
• Date: Mon, 14 Sep 2026 08:49:09 GMT
• Title: Unsupervised Point Cloud Registration via Training-Time Semantic Guidance
• Abstract summary: CAESAR is a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training.<n>Building on this, a train-only Semantic-Geometric Label Mining performs lightweight, batch-specific teacher refinement and mines reliable pseudo-labels.<n>Experiments on KITTI and nuScenes demonstrate state-of-the-art performance, with pronounced gains on the challenging nuScenes benchmark.
• Score: 46.92635414824713
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised registration of large-scale LiDAR point clouds remains challenging due to the geometric ambiguity inherent in outdoor scenes, which degrades pseudo-label quality and leads to suboptimal convergence, particularly for sparse, low-resolution scans such as those from nuScenes. We reveal that registration models intrinsically encode semantic awareness that strongly correlates with registration accuracy, albeit without explicit semantic supervision. However, this native awareness is fragile: noisy supervision arising from geometric ambiguity in unsupervised settings rapidly erodes the learned semantic structure, causing performance collapse. To this end, we propose CAESAR, a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training. We observe that potential inlier matches are often buried just beneath a few spurious neighbors in the noisy feature space, motivating Dual-Cue Guided Re-Matching to recover them through reselection rather than simply rejecting. Building on this, a train-only Semantic-Geometric Label Mining performs lightweight, batch-specific teacher refinement and mines reliable pseudo-labels under semantic guidance. We further introduce Semantic Predictive Distillation to consolidate the student's semantic awareness in the feature space. Extensive experiments on KITTI and nuScenes demonstrate state-of-the-art performance, with pronounced gains on the challenging nuScenes benchmark. Crucially, CAESAR incurs zero inference overhead and requires no semantic annotations on the registration data. Code will be released.

Related papers

• GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure [58.617405464262646]
  3D object detection from LiDAR point clouds is a core problem in autonomous driving.<n>Recent advances in self-supervised learning (SSL) enable scalable pretraining and transfers well to per-point tasks.<n>We analyze recent SSL methods and find that most objectives are defined only on measured LiDAR returns from visible surfaces.<n>We propose GhostPoint, an SSL framework that hallucinates latent features in local neighborhoods around discovered instances.
  arXiv  Detail & Related papers  (2026-08-14T16:10:35Z)
• Weakly Supervised Incremental Segmentation via Semantic Anchors and Spatial Arbitration [8.498917049783191]
  SASA is designed to stabilize semantic learning via Semantic Anchors and Spatial Arbitration.<n>At the representation level, we introduce semantic anchors of learnable tokens as rigid class-level references to preserve long-term semantic identity.<n>At the supervision level, we develop a Spatial Label Arbitration mechanism that performs geometry-aware decisions to directly filter unreliable signals and enforce a strict "one object, one class" constraint.
  arXiv  Detail & Related papers  (2026-06-02T12:10:46Z)
• EAUWSeg: Eliminating annotation uncertainty in weakly-supervised medical image segmentation [4.334357692599945]
  Weakly-supervised medical image segmentation is gaining traction as it requires only rough annotations rather than accurate pixel-to-pixel labels.<n>We propose a novel weak annotation method coupled with its learning framework EAUWSeg to eliminate the annotation uncertainty.<n>We show that EAUWSeg outperforms existing weakly-supervised segmentation methods.
  arXiv  Detail & Related papers  (2025-01-03T06:21:02Z)
• Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration [23.909530805458605]
  Motivated by this observation, we propose a novel unsupervised registration method termed INTEGER to incorporate high-level contextual information for reliable pseudo-label mining.<n>Specifically, we propose the Feature-Geometry Coherence Mining module to dynamically adapt the teacher for each mini-batch of data during training and discover reliable pseudo-labels.<n> Lastly, we introduce a Mixed-Density Student to learn density-invariant features, addressing challenges related to density variation and low overlap in the outdoor scenario.
  arXiv  Detail & Related papers  (2024-11-04T07:57:44Z)
• Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt [80.43623986759691]
  We introduce a novel Unsupervised Continual Anomaly Detection framework called UCAD. The framework equips the UAD with continual learning capability through contrastively-learned prompts. We conduct comprehensive experiments and set the benchmark on unsupervised continual anomaly detection and segmentation.
  arXiv  Detail & Related papers  (2024-01-02T03:37:11Z)
• 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation [92.17700318483745]
  We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network. IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points.
  arXiv  Detail & Related papers  (2023-11-27T07:57:29Z)
• Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation [90.2445084743881]
  We present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance. Inspired by the recent contrastive loss in self-supervised tasks, we propose the guided point contrastive loss to enhance the feature representation and model generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T16:38:54Z)
• Semi-supervised Left Atrium Segmentation with Mutual Consistency Training [60.59108570938163]
  We propose a novel Mutual Consistency Network (MC-Net) for semi-supervised left atrium segmentation from 3D MR images. Our MC-Net consists of one encoder and two slightly different decoders, and the prediction discrepancies of two decoders are transformed as an unsupervised loss. We evaluate our MC-Net on the public Left Atrium (LA) database and it obtains impressive performance gains by exploiting the unlabeled data effectively.
  arXiv  Detail & Related papers  (2021-03-04T09:34:32Z)
• Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace [21.321005898976253]
  Scribble-supervised semantic segmentation has gained much attention recently for its promising performance without high-quality annotations. This work aims to achieve semantic segmentation by scribble annotations directly without extra information and other limitations. We propose holistic operations, including minimizing entropy and a network embedded random walk on neural representation to reduce uncertainty.
  arXiv  Detail & Related papers  (2021-02-19T12:33:57Z)
• Weakly Supervised Vessel Segmentation in X-ray Angiograms by Self-Paced Learning from Noisy Labels with Suggestive Annotation [12.772031281511023]
  We propose a weakly supervised training framework that learns from noisy pseudo labels generated from automatic vessel enhancement. A typical self-paced learning scheme is used to make the training process robust against label noise. We show that our proposed framework achieves comparable accuracy to fully supervised learning.
  arXiv  Detail & Related papers  (2020-05-27T13:55:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.