# Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness

arXiv: https://arxiv.org/abs/2107.14342 · HTML: https://mlsanity.com/paper/2107.14342/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 29 Jul 2021.

## Builds on (most cited first, 22 of 22)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [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)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2012.03015/) (2020)
- [AFDet: Anchor Free One Stage 3D Object Detection](https://mlsanity.com/paper/2006.12671/) (2020)
- [IoU-aware Single-stage Object Detector for Accurate Localization](https://mlsanity.com/paper/1912.05992/) (2019)
- [SWA Object Detection](https://mlsanity.com/paper/2012.12645/) (2020)
- [1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation](https://mlsanity.com/paper/2006.15505/) (2020)
- [1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking](https://mlsanity.com/paper/2006.15506/) (2020)

## Built on by (most cited first, 4 of 4)

- [AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds](https://mlsanity.com/paper/2112.09205/) (2021)
- [Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion](https://mlsanity.com/paper/2203.09780/) (2022)
- [CG-SSD: Corner Guided Single Stage 3D Object Detection from LiDAR Point Cloud](https://mlsanity.com/paper/2202.11868/) (2022)
- [MT-Net Submission to the Waymo 3D Detection Leaderboard](https://mlsanity.com/paper/2207.04781/) (2022)

## Abstract (arXiv)

In this report, we introduce our winning solution to the Real-time 3D Detection and also the "Most Efficient Model" in the Waymo Open Dataset Challenges at CVPR 2021. Extended from our last year's award-winning model AFDet, we have made a handful of modifications to the base model, to improve the accuracy and at the same time to greatly reduce the latency. The modified model, named as AFDetV2, is featured with a lite 3D Feature Extractor, an improved RPN with extended receptive field and an added sub-head that produces an IoU-aware confidence score. These model enhancements, together with enriched data augmentation, stochastic weights averaging, and a GPU-based implementation of voxelization, lead to a winning accuracy of 73.12 mAPH/L2 for our AFDetV2 with a latency of 60.06 ms, and an accuracy of 72.57 mAPH/L2 for our AFDetV2-base, entitled as the "Most Efficient Model" by the challenge sponsor, with a winning latency of 55.86 ms.