# VPFNet: Voxel-Pixel Fusion Network for Multi-class 3D Object Detection

arXiv: https://arxiv.org/abs/2111.00966 · HTML: https://mlsanity.com/paper/2111.00966/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 21 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 19 of 19)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://mlsanity.com/paper/1712.02294/) (2017)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection](https://mlsanity.com/paper/1903.01864/) (2019)
- [TANet: Robust 3D Object Detection from Point Clouds with Triple Attention](https://mlsanity.com/paper/1912.05163/) (2019)
- [DSGN: Deep Stereo Geometry Network for 3D Object Detection](https://mlsanity.com/paper/2001.03398/) (2020)
- [Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots](https://mlsanity.com/paper/1912.12791/) (2019)
- [PI-RCNN: An Efficient Multi-sensor 3D Object Detector with Point-based Attentive Cont-conv Fusion Module](https://mlsanity.com/paper/1911.06084/) (2019)
- [Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using Fusion](https://mlsanity.com/paper/2011.01404/) (2020)
- [MLOD: A multi-view 3D object detection based on robust feature fusion method](https://mlsanity.com/paper/1909.04163/) (2019)

## Built on by (most cited first, 2 of 2)

- [CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection](https://mlsanity.com/paper/2204.00325/) (2022)
- [DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection](https://mlsanity.com/paper/2203.09510/) (2022)

## Abstract (arXiv)

Many LiDAR-based methods for detecting large objects, single-class object detection, or under easy situations were claimed to perform quite well. However, their performances of detecting small objects or under hard situations did not surpass those of the fusion-based ones due to failure to leverage the image semantics. In order to elevate the detection performance in a complicated environment, this paper proposes a deep learning (DL)-embedded fusion-based multi-class 3D object detection network which admits both LiDAR and camera sensor data streams, named Voxel-Pixel Fusion Network (VPFNet). Inside this network, a key novel component is called Voxel-Pixel Fusion (VPF) layer, which takes advantage of the geometric relation of a voxel-pixel pair and fuses the voxel features and the pixel features with proper mechanisms. Moreover, several parameters are particularly designed to guide and enhance the fusion effect after considering the characteristics of a voxel-pixel pair. Finally, the proposed method is evaluated on the KITTI benchmark for multi-class 3D object detection task under multilevel difficulty, and is shown to outperform all state-of-the-art methods in mean average precision (mAP). It is also noteworthy that our approach here ranks the first on the KITTI leaderboard for the challenging pedestrian class.