# Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation

arXiv: https://arxiv.org/abs/2011.14589 · HTML: https://mlsanity.com/paper/2011.14589/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image](https://mlsanity.com/paper/2109.06161/) (2021)
- [Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview](https://mlsanity.com/paper/2105.14291/) (2021)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles](https://mlsanity.com/paper/2206.10255/) (2022)
- [Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Framework](https://mlsanity.com/paper/2212.04111/) (2022)
- [An Intuitive and Unconstrained 2D Cube Representation for Simultaneous Head Detection and Pose Estimation](https://mlsanity.com/paper/2212.03623/) (2022)
- [SoK: Vehicle Orientation Representations for Deep Rotation Estimation](https://mlsanity.com/paper/2112.04421/) (2021)
- [IDMS: Instance Depth for Multi-scale Monocular 3D Object Detection](https://mlsanity.com/paper/2212.01528/) (2022)
- [Multi-scale Feature Fusion with Point Pyramid for 3D Object Detection](https://mlsanity.com/paper/2409.04601/) (2024)

## Abstract (arXiv)

Monocular 3D object detection, with the aim of predicting the geometric properties of on-road objects, is a promising research topic for the intelligent perception systems of autonomous driving. Most state-of-the-art methods follow a keypoint-based paradigm, where the keypoints of objects are predicted and employed as the basis for regressing the other geometric properties. In this work, a unified network named as FADNet is presented to address the task of monocular 3D object detection. In contrast to previous keypoint-based methods, we propose to divide the output modalities into different groups according to the estimation difficulty of object properties. Different groups are treated differently and sequentially associated by a convolutional Gated Recurrent Unit. Another contribution of this work is the strategy of depth hint augmentation. To provide characterized depth patterns as hints for depth estimation, a dedicated depth hint module is designed to generate row-wise features named as depth hints, which are explicitly supervised in a bin-wise manner. The contributions of this work are validated by conducting experiments and ablation study on the KITTI benchmark. Without utilizing depth priors, post optimization, or other refinement modules, our network performs competitively against state-of-the-art methods while maintaining a decent running speed.