Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation

• URL: http://arxiv.org/abs/2506.17891v1
• Date: Sun, 22 Jun 2025 03:48:19 GMT
• Title: Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation
• Authors: Jiahao Lu, Jiacheng Deng,
• Abstract summary: 3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels.<n>We introduce textbfRelation3D: Enhancing Relation Modeling for Point Instance. Specifically, we introduce an adaptive superpoint aggregation module and a contrastive learning-guided superpoint refinement module to better represent superpoint features (scene features)<n>Our relation-aware self-attention mechanism enhances the capabilities of modeling relationships between queries by incorporating positional and geometric relationships into the self-attention mechanism.
• Score: 4.476845464695504
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to their elegant pipelines and superior predictions. However, these methods primarily focus on modeling the external relationships between scene features and query features through mask attention. They lack effective modeling of the internal relationships among scene features as well as between query features. In light of these disadvantages, we propose \textbf{Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation}. Specifically, we introduce an adaptive superpoint aggregation module and a contrastive learning-guided superpoint refinement module to better represent superpoint features (scene features) and leverage contrastive learning to guide the updates of these features. Furthermore, our relation-aware self-attention mechanism enhances the capabilities of modeling relationships between queries by incorporating positional and geometric relationships into the self-attention mechanism. Extensive experiments on the ScanNetV2, ScanNet++, ScanNet200 and S3DIS datasets demonstrate the superior performance of Relation3D.

Related papers

• EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting [108.15136508964011]
  EgoSplat is a language-embedded 3D Gaussian Splatting framework for open-vocabulary egocentric scene understanding.<n>EgoSplat achieves state-of-the-art performance in both localization and segmentation tasks on two datasets.
  arXiv  Detail & Related papers  (2025-03-14T12:21:26Z)
• VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding [9.048401253308123]
  This paper investigates flexible organization and explicit correlation learning for multiple views. We devise a nimble Transformer model, named emphVSFormer, to explicitly capture pairwise and higher-order correlations of all elements in the set. It reaches state-of-the-art results on various 3d recognition datasets, including ModelNet40, ScanObjectNN and RGBD.
  arXiv  Detail & Related papers  (2024-09-14T01:48:54Z)
• Appearance-Based Refinement for Object-Centric Motion Segmentation [85.2426540999329]
  We introduce an appearance-based refinement method that leverages temporal consistency in video streams to correct inaccurate flow-based proposals. Our approach involves a sequence-level selection mechanism that identifies accurate flow-predicted masks as exemplars. Its performance is evaluated on multiple video segmentation benchmarks, including DAVIS, YouTube, SegTrackv2, and FBMS-59.
  arXiv  Detail & Related papers  (2023-12-18T18:59:51Z)
• ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models [77.84408427496025]
  State-of-the-art 3D point cloud registration methods rely on labeled 3D datasets for training.<n>We introduce ZeroReg, a zero-shot registration approach that utilizes 2D foundation models to predict 3D correspondences.
  arXiv  Detail & Related papers  (2023-12-05T11:33:16Z)
• Position-Guided Point Cloud Panoptic Segmentation Transformer [118.17651196656178]
  This work begins by applying this appealing paradigm to LiDAR-based point cloud segmentation and obtains a simple yet effective baseline. We observe that instances in the sparse point clouds are relatively small to the whole scene and often have similar geometry but lack distinctive appearance for segmentation, which are rare in the image domain. The method, named Position-guided Point cloud Panoptic segmentation transFormer (P3Former), outperforms previous state-of-the-art methods by 3.4% and 1.2% on Semantic KITTI and nuScenes benchmark, respectively.
  arXiv  Detail & Related papers  (2023-03-23T17:59:02Z)
• Part-guided Relational Transformers for Fine-grained Visual Recognition [59.20531172172135]
  We propose a framework to learn the discriminative part features and explore correlations with a feature transformation module. Our proposed approach does not rely on additional part branches and reaches state-the-of-art performance on 3-of-the-level object recognition.
  arXiv  Detail & Related papers  (2022-12-28T03:45:56Z)
• Spatio-Temporal Relation Learning for Video Anomaly Detection [35.59510027883497]
  Anomaly identification is highly dependent on the relationship between the object and the scene. In this paper, we propose a Spatial-Temporal Relation Learning framework to tackle the video anomaly detection task. Experiments are conducted on three public datasets, and the superior performance over the state-of-the-art methods demonstrates the effectiveness of our method.
  arXiv  Detail & Related papers  (2022-09-27T02:19:31Z)
• DFC: Deep Feature Consistency for Robust Point Cloud Registration [0.4724825031148411]
  We present a novel learning-based alignment network for complex alignment scenes. We validate our approach on the 3DMatch dataset and the KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-11-15T08:27:21Z)
• Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation [12.093182949686781]
  We propose a novel 3D point cloud learning network, referred to as Dynamic Point Feature Aggregation Network (DPFA-Net) DPFA-Net has two variants for semantic segmentation and classification of 3D point clouds. It achieves the state-of-the-art overall accuracy score for semantic segmentation on the S3DIS dataset.
  arXiv  Detail & Related papers  (2021-11-14T05:46:05Z)
• SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection [9.924083358178239]
  We propose two variants of self-attention for contextual modeling in 3D object detection. We first incorporate the pairwise self-attention mechanism into the current state-of-the-art BEV, voxel and point-based detectors. Next, we propose a self-attention variant that samples a subset of the most representative features by learning deformations over randomly sampled locations.
  arXiv  Detail & Related papers  (2021-01-07T18:30:32Z)
• Improving Point Cloud Semantic Segmentation by Learning 3D Object Detection [102.62963605429508]
  Point cloud semantic segmentation plays an essential role in autonomous driving. Current 3D semantic segmentation networks focus on convolutional architectures that perform great for well represented classes. We propose a novel Aware 3D Semantic Detection (DASS) framework that explicitly leverages localization features from an auxiliary 3D object detection task.
  arXiv  Detail & Related papers  (2020-09-22T14:17:40Z)
• Improving Semantic Segmentation via Decoupled Body and Edge Supervision [89.57847958016981]
  Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for semantic segmentation is proposed. Our insight is that appealing performance of semantic segmentation requires textitexplicitly modeling the object textitbody and textitedge, which correspond to the high and low frequency of the image. We show that the proposed framework with various baselines or backbone networks leads to better object inner consistency and object boundaries.
  arXiv  Detail & Related papers  (2020-07-20T12:11:22Z)

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.