SAGE3D: Soft-guided attention and graph excitation for 3D point cloud corner detection

• URL: http://arxiv.org/abs/2605.15088v1
• Date: Thu, 14 May 2026 17:08:35 GMT
• Title: SAGE3D: Soft-guided attention and graph excitation for 3D point cloud corner detection
• Abstract summary: We present SAGE3D, a hybrid Transformer-based model for corner detection in airborne LiDAR point clouds.<n>We propose a multi-stage solution built on a hierarchical encoder-decoder architecture that progressively downsamples point clouds.<n>We introduce two innovations: Soft-Guided Attention and Excitatory Graph Neural Network.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present SAGE3D, a hybrid Transformer-based model for corner detection in airborne LiDAR point clouds. We propose a multi-stage solution built on a hierarchical encoder-decoder architecture that progressively downsamples point clouds through Set Abstraction layers and recovers per-point predictions via Feature Propagation. We introduce two innovations: Soft-Guided Attention, which injects ground-truth corner labels as a log-prior into attention logits during training to improve precision; then an Excitatory Graph Neural Network positioned at strategic resolutions in the hierarchy, employing positive-only message passing where high-confidence corners reinforce predictions through learned boosting, optimizing for recall. The hierarchical design enables multi-scale feature extraction while our guided attention and excitatory modules ensure corner signals are amplified rather than diluted across scales.

Related papers

• LitePT: Lighter Yet Stronger Point Transformer [50.6430530112838]
  We analyse the role of different computational blocks in 3D point cloud networks.<n>We propose a new, improved 3D point cloud backbone that employs convolutions in early stages and switches to attention for deeper layers.<n>The resulting LitePT model has $3.6times$ fewer parameters, runs $2times$ faster, and uses $2times$ less memory than the state-of-the-art Point Transformer V3.
  arXiv  Detail & Related papers  (2025-12-15T18:59:57Z)
• 3D Point Cloud Generation via Autoregressive Up-sampling [60.05226063558296]
  We introduce a pioneering autoregressive generative model for 3D point cloud generation.<n>Inspired by visual autoregressive modeling, we conceptualize point cloud generation as an autoregressive up-sampling process.<n>PointARU progressively refines 3D point clouds from coarse to fine scales.
  arXiv  Detail & Related papers  (2025-03-11T16:30:45Z)
• DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection [42.07920565812081]
  We propose a novel post-training weight pruning scheme for 3D object detection. It determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence. This framework aims to minimize detection distortion of network output to maximally maintain detection precision.
  arXiv  Detail & Related papers  (2024-07-02T09:33:32Z)
• KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection [48.66703222700795]
  We resort to a novel kernel strategy to identify the most informative point clouds to acquire labels. To accommodate both one-stage (i.e., SECOND) and two-stage detectors, we incorporate the classification entropy tangent and well trade-off between detection performance and the total number of bounding boxes selected for annotation. Our results show that approximately 44% box-level annotation costs and 26% computational time are reduced compared to the state-of-the-art method.
  arXiv  Detail & Related papers  (2023-07-16T04:27:03Z)
• Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysis [14.844183458784235]
  We present an alternative to enhance existing deep neural networks without redesigning or extra parameters, termed as Spatial-Neighbor Adapter (SN-Adapter) Building on any trained 3D network, we utilize its learned encoding capability to extract features of the training dataset and summarize them as spatial knowledge. For a test point cloud, the SN-Adapter retrieves k nearest neighbors (k-NN) from the pre-constructed spatial prototypes and linearly interpolates the k-NN prediction with prototypical that of the original 3D network.
  arXiv  Detail & Related papers  (2023-03-01T17:57:09Z)
• Hierarchical Point Attention for Indoor 3D Object Detection [111.04397308495618]
  This work proposes two novel attention operations as generic hierarchical designs for point-based transformer detectors. First, we propose Multi-Scale Attention (MS-A) that builds multi-scale tokens from a single-scale input feature to enable more fine-grained feature learning. Second, we propose Size-Adaptive Local Attention (Local-A) with adaptive attention regions for localized feature aggregation within bounding box proposals.
  arXiv  Detail & Related papers  (2023-01-06T18:52:12Z)
• MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds [13.426810473131642]
  Masked AutoEncoder for LiDAR point clouds (MAELi) intuitively leverages the sparsity of LiDAR point clouds in both the encoder and decoder during reconstruction. In a novel reconstruction approach, MAELi distinguishes between empty and occluded space. Thereby, without any ground truth whatsoever and trained on single frames only, MAELi obtains an understanding of the underlying 3D scene geometry and semantics.
  arXiv  Detail & Related papers  (2022-12-14T13:10:27Z)
• Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation [78.6612285236938]
  We propose a novel DAT (textbfDual textbfAdaptive textbfTransformations) model for weakly supervised point cloud segmentation. We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets.
  arXiv  Detail & Related papers  (2022-07-19T05:43:14Z)
• Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning [23.730871202742083]
  unsupervised learning is essential for understanding and utilizing point clouds without an expensive annotation process. We propose a novel framework and an effective auto-encoder architecture named "PSG-Net" for reconstruction-based learning of point clouds. We prove the effectiveness of PSG-Net experimentally; PSG-Net shows state-of-the-art performances in point cloud reconstruction and unsupervised classification, and achieves comparable performance to counterpart methods in supervised completion.
  arXiv  Detail & Related papers  (2021-12-09T21:05:30Z)
• 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)
• PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection [57.49788100647103]
  LiDAR-based 3D object detection is an important task for autonomous driving. Current approaches suffer from sparse and partial point clouds of distant and occluded objects. In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions.
  arXiv  Detail & Related papers  (2020-12-18T18:06:43Z)

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.