# Voxelized 3D Feature Aggregation for Multiview Detection

arXiv: https://arxiv.org/abs/2112.03471 · HTML: https://mlsanity.com/paper/2112.03471/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 7 Dec 2021.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (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)
- [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2012.10992/) (2020)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [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)
- [PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation](https://mlsanity.com/paper/1711.10871/) (2017)
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019)
- [RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving](https://mlsanity.com/paper/2001.03343/) (2020)
- [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://mlsanity.com/paper/1903.10955/) (2019)
- [Geometry-based Distance Decomposition for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.03775/) (2021)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)](https://mlsanity.com/paper/2108.05888/) (2021)
- [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)
- [A Geometric Approach to Obtain a Bird's Eye View from an Image](https://mlsanity.com/paper/1905.02231/) (2019)
- [Training-Time-Friendly Network for Real-Time Object Detection](https://mlsanity.com/paper/1909.00700/) (2019)
- [Generalizable Multi-Camera 3D Pedestrian Detection](https://mlsanity.com/paper/2104.05813/) (2021)
- [MVM3Det: A Novel Method for Multi-view Monocular 3D Detection](https://mlsanity.com/paper/2109.10473/) (2021)

## Built on by (most cited first, 6 of 6)

- [Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction](https://mlsanity.com/paper/2506.23863/) (2025)
- [DCHM: Depth-Consistent Human Modeling for Multiview Detection](https://mlsanity.com/paper/2507.14505/) (2025)
- [CVB: A Video Dataset of Cattle Visual Behaviors](https://mlsanity.com/paper/2305.16555/) (2023)
- [Multiview Detection with Cardboard Human Modeling](https://mlsanity.com/paper/2207.02013/) (2022)
- [Fool the Hydra: Adversarial Attacks against Multi-view Object Detection Systems](https://mlsanity.com/paper/2312.00173/) (2023)
- [Public Computer Vision Datasets for Precision Livestock Farming: A Systematic Survey](https://mlsanity.com/paper/2406.10628/) (2024)

## Abstract (arXiv)

Multi-view detection incorporates multiple camera views to alleviate occlusion in crowded scenes, where the state-of-the-art approaches adopt homography transformations to project multi-view features to the ground plane. However, we find that these 2D transformations do not take into account the object's height, and with this neglection features along the vertical direction of same object are likely not projected onto the same ground plane point, leading to impure ground-plane features. To solve this problem, we propose VFA, voxelized 3D feature aggregation, for feature transformation and aggregation in multi-view detection. Specifically, we voxelize the 3D space, project the voxels onto each camera view, and associate 2D features with these projected voxels. This allows us to identify and then aggregate 2D features along the same vertical line, alleviating projection distortions to a large extent. Additionally, because different kinds of objects (human vs. cattle) have different shapes on the ground plane, we introduce the oriented Gaussian encoding to match such shapes, leading to increased accuracy and efficiency. We perform experiments on multiview 2D detection and multiview 3D detection problems. Results on four datasets (including a newly introduced MultiviewC dataset) show that our system is very competitive compared with the state-of-the-art approaches. %Our code and data will be open-sourced.Code and MultiviewC are released at https://github.com/Robert-Mar/VFA.