GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detection

• URL: http://arxiv.org/abs/2512.23147v1
• Date: Mon, 29 Dec 2025 02:24:18 GMT
• Title: GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detection
• Authors: Jingyu Li, Xiaolong Zhao, Zhe Liu, Wenxiao Wu, Li Zhang,
• Abstract summary: Semi-supervised 3D object detection has emerged as an active research area in recent years.<n>We propose GeoTeacher to enhance the student model's ability to capture geometric relations of objects with limited training data.<n>We introduce a voxel-wise data augmentation strategy that increases the diversity of object geometries.
• Score: 19.447180486374357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semi-supervised 3D object detection, aiming to explore unlabeled data for boosting 3D object detectors, has emerged as an active research area in recent years. Some previous methods have shown substantial improvements by either employing heterogeneous teacher models to provide high-quality pseudo labels or enforcing feature-perspective consistency between the teacher and student networks. However, these methods overlook the fact that the model usually tends to exhibit low sensitivity to object geometries with limited labeled data, making it difficult to capture geometric information, which is crucial for enhancing the student model's ability in object perception and localization. In this paper, we propose GeoTeacher to enhance the student model's ability to capture geometric relations of objects with limited training data, especially unlabeled data. We design a keypoint-based geometric relation supervision module that transfers the teacher model's knowledge of object geometry to the student, thereby improving the student's capability in understanding geometric relations. Furthermore, we introduce a voxel-wise data augmentation strategy that increases the diversity of object geometries, thereby further improving the student model's ability to comprehend geometric structures. To preserve the integrity of distant objects during augmentation, we incorporate a distance-decay mechanism into this strategy. Moreover, GeoTeacher can be combined with different SS3D methods to further improve their performance. Extensive experiments on the ONCE and Waymo datasets indicate the effectiveness and generalization of our method and we achieve the new state-of-the-art results. Code will be available at https://github.com/SII-Whaleice/GeoTeacher

Related papers

• UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating [20.395441875640955]
  We propose a unified 3D indoor detection framework called UniGeo.<n>To model geometric relations in scenes, we first propose a geometry-aware learning module that establishes a learnable mapping from spatial relationships to feature weights.<n>Then, to further enhance point cloud feature representation, we propose a dynamic channel gating mechanism that leverages learnable channel-wise weighting.
  arXiv  Detail & Related papers  (2026-01-30T06:15:50Z)
• GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation [57.8059956428009]
  Recent attempts to transfer features from 2D Vision-Language Models to 3D semantic segmentation expose a persistent trade-off.<n>We propose GeoPurify that applies a small Student Affinity Network to 2D VLM-generated 3D point features using geometric priors distilled from a 3D self-supervised teacher model.<n>Benefiting from latent geometric information and the learned affinity network, GeoPurify effectively mitigates the trade-off and achieves superior data efficiency.
  arXiv  Detail & Related papers  (2025-10-02T16:37:56Z)
• GRACE: Estimating Geometry-level 3D Human-Scene Contact from 2D Images [54.602947113980655]
  Estimating the geometry level of human-scene contact aims to ground specific contact surface points at 3D human geometries.<n> GRACE (Geometry-level Reasoning for 3D Human-scene Contact Estimation) is a new paradigm for 3D human contact estimation.<n>It incorporates a point cloud encoder-decoder architecture along with a hierarchical feature extraction and fusion module.
  arXiv  Detail & Related papers  (2025-05-10T09:25:46Z)
• GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding [53.42728468191711]
  Open-Vocabulary 3D object affordance grounding aims to anticipate action possibilities'' regions on 3D objects with arbitrary instructions.<n>We propose GREAT (GeometRy-intEntion collAboraTive inference) for Open-Vocabulary 3D Object Affordance Grounding.
  arXiv  Detail & Related papers  (2024-11-29T11:23:15Z)
• Geometry Distributions [51.4061133324376]
  We propose a novel geometric data representation that models geometry as distributions. Our approach uses diffusion models with a novel network architecture to learn surface point distributions. We evaluate our representation qualitatively and quantitatively across various object types, demonstrating its effectiveness in achieving high geometric fidelity.
  arXiv  Detail & Related papers  (2024-11-25T04:06:48Z)
• Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection [70.71934539556916]
  We learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection. Specifically, a principled geometry formula with projective modeling of 2D and 3D depth predictions in the monocular 3D object detection network is devised. Our method remarkably improves the detection performance of the state-of-the-art monocular-based method without extra data by 2.80% on the moderate test setting.
  arXiv  Detail & Related papers  (2021-07-29T12:30:39Z)
• Self-supervised Geometric Perception [96.89966337518854]
  Self-supervised geometric perception is a framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels. We show that SGP achieves state-of-the-art performance that is on-par or superior to the supervised oracles trained using ground-truth labels.
  arXiv  Detail & Related papers  (2021-03-04T15:34:43Z)
• Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning [8.448611728105513]
  We propose to extend the InfoMax and contrastive learning principles on 3D shapes. We show that we can maximize the mutual information between 3D objects and their "chunks" to improve the representations in aligned datasets.
  arXiv  Detail & Related papers  (2020-06-04T00:30:26Z)

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.