mlsanityData to 7 Oct 2026

MLF-DET: Multi-Level Fusion for Cross-Modal 3D Object Detection

arXiv 2307.09155 ↗First posted 18 Jul 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel and effective Multi-Level Fusion network, named as MLF-DET, for high-performance cross-modal 3D object DETection, which integrates both the feature-level fusion and decision-level fusion to fully utilize the information in the image. For the feature-level fusion, we present the Multi-scale Voxel Image fusion (MVI) module, which densely aligns multi-scale voxel features with image features. For the decision-level fusion, we propose the lightweight Feature-cued Confidence Rectification (FCR) module which further exploits image semantics to rectify the confidence of detection candidates. Besides, we design an effective data augmentation strategy termed Occlusion-aware GT Sampling (OGS) to reserve more sampled objects in the training scenes, so as to reduce overfitting. Extensive experiments on the KITTI dataset demonstrate the effectiveness of our method. Notably, on the extremely competitive KITTI car 3D object detection benchmark, our method reaches 82.89% moderate AP and achieves state-of-the-art performance without bells and whistles.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 33 references that are in the map. First posted on arXiv 18 Jul 2023.

Builds on

28 of 33 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  8. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  9. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  10. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  11. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  12. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
16 more
  1. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  2. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  3. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 202
  4. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  5. 2020EPNet: Enhancing Point Features with Image Semantics for 3D Object Detectioncited by 164
  6. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  7. 2020CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detectioncited by 147
  8. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  9. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  10. 2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
  11. 2022Voxel Field Fusion for 3D Object Detectioncited by 50
  12. 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
  13. 2021VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusioncited by 48
  14. 2022CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detectioncited by 32
  15. 2022Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detectioncited by 26
  16. 2022Dense Voxel Fusion for 3D Object Detectioncited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object Detectioncited by 2
  2. 2025Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenescited by 2
  3. 2025S-LAM3D: Segmentation-Guided Monocular 3D Object Detection via Feature Space Fusioncited by 0
  4. 2026LCF3D: A Robust and Real-Time Late-Cascade Fusion Framework for 3D Object Detection in Autonomous Drivingcited by 0
  5. 2026Point Virtual Transformercited by 0