# SDVRF: Sparse-to-Dense Voxel Region Fusion for Multi-modal 3D Object Detection

arXiv: https://arxiv.org/abs/2304.08304 · HTML: https://mlsanity.com/paper/2304.08304/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 53 references that are in the map.
- First posted on arXiv 17 Apr 2023.

## Builds on (most cited first, 30 of 40)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [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)
- [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)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2012.10992/) (2020)
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2203.08195/) (2022)
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection](https://mlsanity.com/paper/2004.12636/) (2020)
- [End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/1910.06528/) (2019)
- [EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection](https://mlsanity.com/paper/2007.08856/) (2020)
- [MVX-Net: Multimodal VoxelNet for 3D Object Detection](https://mlsanity.com/paper/1904.01649/) (2019)
- [Focal Sparse Convolutional Networks for 3D Object Detection](https://mlsanity.com/paper/2204.12463/) (2022)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection](https://mlsanity.com/paper/1903.01864/) (2019)
- [SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2104.09804/) (2021)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2207.10035/) (2022)
- [HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection](https://mlsanity.com/paper/2003.00186/) (2020)
- [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)
- [M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers](https://mlsanity.com/paper/2104.11896/) (2021)
- [Point Density-Aware Voxels for LiDAR 3D Object Detection](https://mlsanity.com/paper/2203.05662/) (2022)

## Abstract (arXiv)

In the perception task of autonomous driving, multi-modal methods have become a trend due to the complementary characteristics of LiDAR point clouds and image data. However, the performance of multi-modal methods is usually limited by the sparsity of the point cloud or the noise problem caused by the misalignment between LiDAR and the camera. To solve these two problems, we present a new concept, Voxel Region (VR), which is obtained by projecting the sparse local point clouds in each voxel dynamically. And we propose a novel fusion method named Sparse-to-Dense Voxel Region Fusion (SDVRF). Specifically, more pixels of the image feature map inside the VR are gathered to supplement the voxel feature extracted from sparse points and achieve denser fusion. Meanwhile, different from prior methods, which project the size-fixed grids, our strategy of generating dynamic regions achieves better alignment and avoids introducing too much background noise. Furthermore, we propose a multi-scale fusion framework to extract more contextual information and capture the features of objects of different sizes. Experiments on the KITTI dataset show that our method improves the performance of different baselines, especially on classes of small size, including Pedestrian and Cyclist.