MVX-Net: Multimodal VoxelNet for 3D Object Detection
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Frustum PointNets for 3D Object Detection from RGB-D Data2018
- PIXOR: Real-time 3D Object Detection from Point Clouds2018
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection2018
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- 3D Convolutional Neural Networks for landing zone detection from LiDAR2015
- Pedestrian detection combining RGB and dense LIDAR data2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Point Signatures: A New Representation for 3D Object RecognitionInternational Journal of Computer Vision, 1997
- COSMOS-A representation scheme for 3D free-form objectsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Structural indexing: efficient 3-D object recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992