# MVX-Net: Multimodal VoxelNet for 3D Object Detection

arXiv: https://arxiv.org/abs/1904.01649 · HTML: https://mlsanity.com/paper/1904.01649/

## Key facts

- Cited by 163 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2019.

## Built on by (most cited first, 30 of 163)

- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection](https://mlsanity.com/paper/2204.05575/) (2022)
- [One Million Scenes for Autonomous Driving: ONCE Dataset](https://mlsanity.com/paper/2106.11037/) (2021)
- [Multimodal Virtual Point 3D Detection](https://mlsanity.com/paper/2111.06881/) (2021)
- [ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection](https://mlsanity.com/paper/2106.01178/) (2021)
- [Offboard 3D Object Detection from Point Cloud Sequences](https://mlsanity.com/paper/2103.05073/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling](https://mlsanity.com/paper/2301.03580/) (2023)
- [Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges](https://mlsanity.com/paper/2301.06262/) (2023)
- [Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion](https://mlsanity.com/paper/2203.09780/) (2022)
- [Virtual Sparse Convolution for Multimodal 3D Object Detection](https://mlsanity.com/paper/2303.02314/) (2023)
- [Multi-modal Sensor Fusion for Auto Driving Perception: A Survey](https://mlsanity.com/paper/2202.02703/) (2022)
- [BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection](https://mlsanity.com/paper/2303.08498/) (2023)
- [UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation](https://mlsanity.com/paper/2308.07732/) (2023)
- [AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2201.06493/) (2022)
- [MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2303.08600/) (2023)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency](https://mlsanity.com/paper/2107.11355/) (2021)
- [MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection](https://mlsanity.com/paper/2209.03102/) (2022)
- [SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations](https://mlsanity.com/paper/2112.04680/) (2021)
- [Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection](https://mlsanity.com/paper/2205.14951/) (2022)
- [Voxel Field Fusion for 3D Object Detection](https://mlsanity.com/paper/2205.15938/) (2022)
- [EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2112.11088/) (2021)
- [VPFNet: Improving 3D Object Detection with Virtual Point based LiDAR and Stereo Data Fusion](https://mlsanity.com/paper/2111.14382/) (2021)
- [AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2207.10316/) (2022)
- [Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving](https://mlsanity.com/paper/2101.06784/) (2021)
- [GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer](https://mlsanity.com/paper/2406.01210/) (2024)
- [VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud](https://mlsanity.com/paper/2303.14408/) (2023)

## Abstract (arXiv)

Many recent works on 3D object detection have focused on designing neural network architectures that can consume point cloud data. While these approaches demonstrate encouraging performance, they are typically based on a single modality and are unable to leverage information from other modalities, such as a camera. Although a few approaches fuse data from different modalities, these methods either use a complicated pipeline to process the modalities sequentially, or perform late-fusion and are unable to learn interaction between different modalities at early stages. In this work, we present PointFusion and VoxelFusion: two simple yet effective early-fusion approaches to combine the RGB and point cloud modalities, by leveraging the recently introduced VoxelNet architecture. Evaluation on the KITTI dataset demonstrates significant improvements in performance over approaches which only use point cloud data. Furthermore, the proposed method provides results competitive with the state-of-the-art multimodal algorithms, achieving top-2 ranking in five of the six bird's eye view and 3D detection categories on the KITTI benchmark, by using a simple single stage network.