Fusion4CA: Boosting 3D Object Detection via Comprehensive Image Exploitation

• URL: http://arxiv.org/abs/2603.05305v1
• Date: Thu, 05 Mar 2026 15:46:14 GMT
• Title: Fusion4CA: Boosting 3D Object Detection via Comprehensive Image Exploitation
• Abstract summary: Fusion4CA is built upon the classic BEVFusion framework and dedicated to fully exploiting visual input with plug-and-play components.<n>Our method achieves 69.7% mAP with only 6 training epochs and a mere 3.48% increase in inference parameters.
• Score: 18.857802421595235
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Nowadays, an increasing number of works fuse LiDAR and RGB data in the bird's-eye view (BEV) space for 3D object detection in autonomous driving systems. However, existing methods suffer from over-reliance on the LiDAR branch, with insufficient exploration of RGB information. To tackle this issue, we propose Fusion4CA, which is built upon the classic BEVFusion framework and dedicated to fully exploiting visual input with plug-and-play components. Specifically, a contrastive alignment module is designed to calibrate image features with 3D geometry, and a camera auxiliary branch is introduced to mine RGB information sufficiently during training. For further performance enhancement, we leverage an off-the-shelf cognitive adapter to make the most of pretrained image weights, and integrate a standard coordinate attention module into the fusion stage as a supplementary boost. Experiments on the nuScenes dataset demonstrate that our method achieves 69.7% mAP with only 6 training epochs and a mere 3.48% increase in inference parameters, yielding a 1.2% improvement over the baseline which is fully trained for 20 epochs. Extensive experiments in a simulated lunar environment further validate the effectiveness and generalization of our method. Our code will be released through Fusion4CA.

Related papers

• GaussianCaR: Gaussian Splatting for Efficient Camera-Radar Fusion [8.829313789934693]
  Experimental results demonstrate that our approach achieves performance on par with, or even surpassing, the state of the art on BEV segmentation tasks.<n>Our main contribution is GaussianCaR, an end-to-end network for BEV segmentation.
  arXiv  Detail & Related papers  (2026-02-09T15:25:19Z)
• Enhancing Pseudo-Boxes via Data-Level LiDAR-Camera Fusion for Unsupervised 3D Object Detection [18.684602624559734]
  We propose a novel data-level fusion framework that integrates RGB images and LiDAR data at an early stage.<n>We propose a data-level fusion based dynamic self-evolution strategy, which iteratively refines pseudo-boxes under a dense representation.<n>Experiments on the nuScenes dataset demonstrate that the detector trained by our method significantly outperforms that trained by previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-28T08:15:23Z)
• CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection [11.109888378081187]
  We propose a cross-view two-stage fusion network called CVFusion.<n>In the first stage, we design a radar guided iterative (RGIter) BEV fusion module to generate high-recall 3D proposal boxes.<n>In the second stage, we aggregate features from multiple heterogeneous views including points, image, and BEV for each proposal.<n>Our method outperforms the previous state-of-the-art methods by a large margin, with 9.10% and 3.68% mAP improvements on View-of-Delft (VoD) and TJ4DRadSet, respectively.
  arXiv  Detail & Related papers  (2025-07-07T00:45:53Z)
• RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion [58.77329237533034]
  We propose a Radar-Camera fusion transformer (RaCFormer) to boost the accuracy of 3D object detection.<n>RaCFormer achieves superior results of 64.9% mAP and 70.2% on nuScenes datasets.
  arXiv  Detail & Related papers  (2024-12-17T09:47:48Z)
• 4D Contrastive Superflows are Dense 3D Representation Learners [62.433137130087445]
  We introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing pretraining objectives. To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances alignment of the knowledge distilled from camera views.
  arXiv  Detail & Related papers  (2024-07-08T17:59:54Z)
• AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer [5.287142970575824]
  We introduce AYDIV, a novel framework integrating a tri-phase alignment process specifically designed to enhance long-distance detection. AYDIV's performance on the Open dataset (WOD) with an improvement of 1.24% in mAPH value(L2 difficulty) and the Argoverse2 dataset with a performance improvement of 7.40% in AP value.
  arXiv  Detail & Related papers  (2024-02-12T14:40:43Z)
• Geometric-aware Pretraining for Vision-centric 3D Object Detection [77.7979088689944]
  We propose a novel geometric-aware pretraining framework called GAPretrain. GAPretrain serves as a plug-and-play solution that can be flexibly applied to multiple state-of-the-art detectors. We achieve 46.2 mAP and 55.5 NDS on the nuScenes val set using the BEVFormer method, with a gain of 2.7 and 2.1 points, respectively.
  arXiv  Detail & Related papers  (2023-04-06T14:33:05Z)
• BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregation [14.606324706328106]
  We propose a dual-branch framework to generate LiDAR and camera BEV, then perform an adaptive modality fusion. A LiDAR-Guided View Transformer (LGVT) is designed to effectively obtain the camera representation in BEV space. Our framework dubbed BEVFusion4D achieves state-of-the-art results in 3D object detection.
  arXiv  Detail & Related papers  (2023-03-30T02:18:07Z)
• BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios [51.285561119993105]
  We present BEV-MAE, an efficient masked autoencoder pre-training framework for LiDAR-based 3D object detection in autonomous driving. Specifically, we propose a bird's eye view (BEV) guided masking strategy to guide the 3D encoder learning feature representation. We introduce a learnable point token to maintain a consistent receptive field size of the 3D encoder.
  arXiv  Detail & Related papers  (2022-12-12T08:15:03Z)
• 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)
• BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation [105.96557764248846]
  We introduce BEVFusion, a generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye view representation space. It achieves 1.3% higher mAP and NDS on 3D object detection and 13.6% higher mIoU on BEV map segmentation, with 1.9x lower cost.
  arXiv  Detail & Related papers  (2022-05-26T17:59:35Z)
• EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation [62.210091681352914]
  We study multi-sensor fusion for 3D semantic segmentation for many applications, such as autonomous driving and robotics. In this work, we investigate a collaborative fusion scheme called perception-aware multi-sensor fusion (PMF) We propose a two-stream network to extract features from the two modalities separately. The extracted features are fused by effective residual-based fusion modules.
  arXiv  Detail & Related papers  (2021-06-21T10:47:26Z)

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.