Multi-Modal Decouple and Recouple Network for Robust 3D Object Detection

• URL: http://arxiv.org/abs/2603.07486v1
• Date: Sun, 08 Mar 2026 06:10:25 GMT
• Title: Multi-Modal Decouple and Recouple Network for Robust 3D Object Detection
• Abstract summary: We propose a Multi-Modal Decouple and Recouple Network for robust 3D object detection under data corruption.<n>Our model consistently achieves the best accuracy on both corrupted and clean data compared to recent models.
• Score: 20.541042952048862
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal 3D object detection with bird's eye view (BEV) has achieved desired advances on benchmarks. Nonetheless, the accuracy may drop significantly in the real world due to data corruption such as sensor configurations for LiDAR and scene conditions for camera. One design bottleneck of previous models resides in the tightly coupling of multi-modal BEV features during fusion, which may degrade the overall system performance if one modality or both is corrupted. To mitigate, we propose a Multi-Modal Decouple and Recouple Network for robust 3D object detection under data corruption. Different modalities commonly share some high-level invariant features. We observe that these invariant features across modalities do not always fail simultaneously, because different types of data corruption affect each modality in distinct ways.These invariant features can be recovered across modalities for robust fusion under data corruption.To this end, we explicitly decouple Camera/LiDAR BEV features into modality-invariant and modality-specific parts. It allows invariant features to compensate each other while mitigates the negative impact of a corrupted modality on the other.We then recouple these features into three experts to handle different types of data corruption, respectively, i.e., LiDAR, camera, and both.For each expert, we use modality-invariant features as robust information, while modality-specific features serve as a complement.Finally, we adaptively fuse the three experts to exact robust features for 3D object detection. For validation, we collect a benchmark with a large quantity of data corruption for LiDAR, camera, and both based on nuScenes. Our model is trained on clean nuScenes and tested on all types of data corruption. Our model consistently achieves the best accuracy on both corrupted and clean data compared to recent models.

Related papers

• SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions [24.4820890251407]
  We develop a framework-agnostic fusion module for camera and LiDAR data.<n>Our module achieves favorable performance improvements under scenarios of missing and corrupted modalities.
  arXiv  Detail & Related papers  (2026-05-12T08:57:15Z)
• Robust Multimodal 3D Object Detection via Modality-Agnostic Decoding and Proximity-based Modality Ensemble [15.173314907900842]
  Existing 3D object detection methods rely heavily on the LiDAR sensor. We propose MEFormer to address the LiDAR over-reliance problem. Our MEFormer achieves state-of-the-art performance of 73.9% NDS and 71.5% mAP in the nuScenes validation set.
  arXiv  Detail & Related papers  (2024-07-27T03:21:44Z)
• MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection [38.6421466851974]
  We propose a novel online test-time adaptation framework for 3D detectors.<n>By leveraging long-term knowledge from previous test batches, our approach mitigates catastrophic forgetting and adapts effectively to diverse shifts.<n>Our method was rigorously tested against existing test-time adaptation strategies across three datasets and eight types of corruptions.
  arXiv  Detail & Related papers  (2024-06-21T05:58:19Z)
• MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object Detection [5.462358595564476]
  Multi-modal 3D object detection models for automated driving have demonstrated exceptional performance on computer vision benchmarks like nuScenes. However, their reliance on densely sampled LiDAR point clouds and meticulously calibrated sensor arrays poses challenges for real-world applications. We introduce MultiCorrupt, a benchmark designed to evaluate the robustness of multi-modal 3D object detectors against ten distinct types of corruptions.
  arXiv  Detail & Related papers  (2024-02-18T18:56:13Z)
• 3D Adversarial Augmentations for Robust Out-of-Domain Predictions [115.74319739738571]
  We focus on improving the generalization to out-of-domain data. We learn a set of vectors that deform the objects in an adversarial fashion. We perform adversarial augmentation by applying the learned sample-independent vectors to the available objects when training a model.
  arXiv  Detail & Related papers  (2023-08-29T17:58:55Z)
• Multi-Modal 3D Object Detection by Box Matching [109.43430123791684]
  We propose a novel Fusion network by Box Matching (FBMNet) for multi-modal 3D detection. With the learned assignments between 3D and 2D object proposals, the fusion for detection can be effectively performed by combing their ROI features.
  arXiv  Detail & Related papers  (2023-05-12T18:08:51Z)
• Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving [44.753797839280516]
  Existing 3D detectors lack robustness to real-world corruptions caused by adverse weathers, sensor noises, etc. We benchmark 27 types of common corruptions for both LiDAR and camera inputs considering real-world driving scenarios. We conduct large-scale experiments on 24 diverse 3D object detection models to evaluate their robustness.
  arXiv  Detail & Related papers  (2023-03-20T11:45:54Z)
• GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [70.75100533512021]
  In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects. We propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables. The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors.
  arXiv  Detail & Related papers  (2022-07-06T06:26:17Z)
• Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection [58.81316192862618]
  Two critical sensors for 3D perception in autonomous driving are the camera and the LiDAR. fusing these two modalities can significantly boost the performance of 3D perception models. We benchmark the state-of-the-art fusion methods for the first time.
  arXiv  Detail & Related papers  (2022-05-30T09:35:37Z)
• Homography Loss for Monocular 3D Object Detection [54.04870007473932]
  A differentiable loss function, termed as Homography Loss, is proposed to achieve the goal, which exploits both 2D and 3D information. Our method yields the best performance compared with the other state-of-the-arts by a large margin on KITTI 3D datasets.
  arXiv  Detail & Related papers  (2022-04-02T03:48:03Z)
• 3D-VField: Learning to Adversarially Deform Point Clouds for Robust 3D Object Detection [111.32054128362427]
  In safety-critical settings, robustness on out-of-distribution and long-tail samples is fundamental to circumvent dangerous issues. We substantially improve the generalization of 3D object detectors to out-of-domain data by taking into account deformed point clouds during training. We propose and share open source CrashD: a synthetic dataset of realistic damaged and rare cars.
  arXiv  Detail & Related papers  (2021-12-09T08:50:54Z)

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.