GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection

• URL: http://arxiv.org/abs/2503.08639v1
• Date: Tue, 11 Mar 2025 17:29:56 GMT
• Title: GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection
• Authors: Dušan Malić, Christian Fruhwirth-Reisinger, Samuel Schulter, Horst Possegger,
• Abstract summary: Domain Generalization aims to mitigate this by training detectors that are invariant to such domain shifts.<n>We propose to exploit explicit local point cloud structure for DG, in particular by encoding point cloud neighborhoods with Gaussian blobs, GBlobs.<n>Our proposed formulation is highly efficient and requires no additional parameters.
• Score: 12.282805218676208
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LiDAR-based 3D detectors need large datasets for training, yet they struggle to generalize to novel domains. Domain Generalization (DG) aims to mitigate this by training detectors that are invariant to such domain shifts. Current DG approaches exclusively rely on global geometric features (point cloud Cartesian coordinates) as input features. Over-reliance on these global geometric features can, however, cause 3D detectors to prioritize object location and absolute position, resulting in poor cross-domain performance. To mitigate this, we propose to exploit explicit local point cloud structure for DG, in particular by encoding point cloud neighborhoods with Gaussian blobs, GBlobs. Our proposed formulation is highly efficient and requires no additional parameters. Without any bells and whistles, simply by integrating GBlobs in existing detectors, we beat the current state-of-the-art in challenging single-source DG benchmarks by over 21 mAP (Waymo->KITTI), 13 mAP (KITTI->Waymo), and 12 mAP (nuScenes->KITTI), without sacrificing in-domain performance. Additionally, GBlobs demonstrate exceptional performance in multi-source DG, surpassing the current state-of-the-art by 17, 12, and 5 mAP on Waymo, KITTI, and ONCE, respectively.

Related papers

• Generative Classifier for Domain Generalization [84.92088101715116]
  Domain generalization aims to the generalizability of computer vision models toward distribution shifts. We propose Generative-driven Domain Generalization (GCDG) GCDG consists of three key modules: Heterogeneity Learning(HLC), Spurious Correlation(SCB), and Diverse Component Balancing(DCB)
  arXiv  Detail & Related papers  (2025-04-03T04:38:33Z)
• PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model [77.00221501105788]
  Domain Generalization (DG) has been recently explored to improve the generalizability of point cloud classification.<n>We present the first work that studies the generalizability of state space models (SSMs) in DG PCC.<n>We propose a novel framework, PointDGMamba, that excels in strong generalizability toward unseen domains.
  arXiv  Detail & Related papers  (2024-08-24T12:53:48Z)
• Disentangling Masked Autoencoders for Unsupervised Domain Generalization [57.56744870106124]
  Unsupervised domain generalization is fast gaining attention but is still far from well-studied. Disentangled Masked Auto (DisMAE) aims to discover the disentangled representations that faithfully reveal intrinsic features. DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders.
  arXiv  Detail & Related papers  (2024-07-10T11:11:36Z)
• G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection [55.86838901572496]
  Differentiable Neural Architecture Search (NAS) is known for its high capacity for complex data fitting. Generalizable loss (G-loss) is an OoD-aware objective, preventing NAS from over-fitting. Experimental results on the S-DGOD urban-scene datasets demonstrate that the proposed G-NAS achieves SOTA performance compared to baseline methods.
  arXiv  Detail & Related papers  (2024-02-07T08:57:59Z)
• SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification [44.27324696068285]
  We propose a Single-dataset Unified Generalization (SUG) framework to alleviate the unforeseen domain differences faced by a well-trained source model. Specifically, we first design a Multi-grained Sub-domain Alignment (MSA) method, which can constrain the learned representations to be domain-agnostic and discriminative. Then, a Sample-level Domain-aware Attention (SDA) strategy is presented, which can selectively enhance easy-to-adapt samples from different sub-domains.
  arXiv  Detail & Related papers  (2023-05-16T04:36:04Z)
• Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation [16.857861952638498]
  We study domain generalization for LiDAR semantic segmentation (DG-LSS) Our results confirm a significant gap between methods, evaluated in a cross-domain setting. We propose the first method specifically designed for DG-LSS, which obtains $34.88$ mIoU on the target domain.
  arXiv  Detail & Related papers  (2023-04-23T17:43:29Z)
• SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud [125.9472454212909]
  We present a novel Semi-Supervised Domain Adaptation method for 3D object detection (SSDA3D) SSDA3D includes an Inter-domain Adaptation stage and an Intra-domain Generalization stage. Experiments show that, with only 10% labeled target data, our SSDA3D can surpass the fully-supervised oracle model with 100% target label.
  arXiv  Detail & Related papers  (2022-12-06T09:32:44Z)
• SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation [28.372067223801203]
  In autonomous driving, a LiDAR-based object detector should perform reliably at different geographic locations and under various weather conditions. While recent 3D detection research focuses on improving performance within a single domain, our study reveals that the performance of modern detectors can drop drastically cross-domain. We present Semantic Point Generation (SPG), a general approach to enhance the reliability of LiDAR detectors against domain shifts.
  arXiv  Detail & Related papers  (2021-08-15T10:00:39Z)
• Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency [90.71745178767203]
  Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. Existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world. We study a more realistic setting, unsupervised 3D domain adaptive detection, which only utilizes source domain annotations.
  arXiv  Detail & Related papers  (2021-07-23T17:19:23Z)

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.