# MVM3Det: A Novel Method for Multi-view Monocular 3D Detection

arXiv: https://arxiv.org/abs/2109.10473 · HTML: https://mlsanity.com/paper/2109.10473/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 22 Sep 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://mlsanity.com/paper/1712.02294/) (2017)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [Real-Time Seamless Single Shot 6D Object Pose Prediction](https://mlsanity.com/paper/1711.08848/) (2017)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape](https://mlsanity.com/paper/1812.02781/) (2018)
- [Cooperative Perception for 3D Object Detection in Driving Scenarios using Infrastructure Sensors](https://mlsanity.com/paper/1912.12147/) (2019)
- [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://mlsanity.com/paper/1903.10955/) (2019)
- [Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction](https://mlsanity.com/paper/1904.01690/) (2019)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [Deep Fitting Degree Scoring Network for Monocular 3D Object Detection](https://mlsanity.com/paper/1904.12681/) (2019)
- [Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection](https://mlsanity.com/paper/1704.05775/) (2017)
- [Deep Multi-camera People Detection](https://mlsanity.com/paper/1702.04593/) (2017)
- [MonoGRNet: A General Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.08797/) (2021)
- [BiFNet: Bidirectional Fusion Network for Road Segmentation](https://mlsanity.com/paper/2004.08582/) (2020)

## Built on by (most cited first, 3 of 3)

- [Voxelized 3D Feature Aggregation for Multiview Detection](https://mlsanity.com/paper/2112.03471/) (2021)
- [You Only Look Bottom-Up for Monocular 3D Object Detection](https://mlsanity.com/paper/2401.15319/) (2024)
- [Multiview Detection with Cardboard Human Modeling](https://mlsanity.com/paper/2207.02013/) (2022)

## Abstract (arXiv)

Monocular 3D object detection encounters occlusion problems in many application scenarios, such as traffic monitoring, pedestrian monitoring, etc., which leads to serious false negative. Multi-view object detection effectively solves this problem by combining data from different perspectives. However, due to label confusion and feature confusion, the orientation estimation of multi-view 3D object detection is intractable, which is important for object tracking and intention prediction. In this paper, we propose a novel multi-view 3D object detection method named MVM3Det which simultaneously estimates the 3D position and orientation of the object according to the multi-view monocular information. The method consists of two parts: 1) Position proposal network, which integrates the features from different perspectives into consistent global features through feature orthogonal transformation to estimate the position. 2) Multi-branch orientation estimation network, which introduces feature perspective pooling to overcome the two confusion problems during the orientation estimation. In addition, we present a first dataset for multi-view 3D object detection named MVM3D. Comparing with State-Of-The-Art (SOTA) methods on our dataset and public dataset WildTrack, our method achieves very competitive results.