# Reinforced Axial Refinement Network for Monocular 3D Object Detection

arXiv: https://arxiv.org/abs/2008.13748 · HTML: https://mlsanity.com/paper/2008.13748/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2020.

## Built on by (most cited first, 18 of 18)

- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection](https://mlsanity.com/paper/2112.04628/) (2021)
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey](https://mlsanity.com/paper/2108.11510/) (2021)
- [Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview](https://mlsanity.com/paper/2105.14291/) (2021)
- [MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection](https://mlsanity.com/paper/2203.08563/) (2022)
- [CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection](https://mlsanity.com/paper/2210.09267/) (2022)
- [LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection](https://mlsanity.com/paper/2206.07705/) (2022)
- [MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors](https://mlsanity.com/paper/2410.19590/) (2024)
- [Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13931/) (2021)
- [Exploring Geometric Consistency for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.05858/) (2021)
- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection](https://mlsanity.com/paper/2211.01556/) (2022)
- [GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2310.15624/) (2023)
- [Stereo Neural Vernier Caliper](https://mlsanity.com/paper/2203.11018/) (2022)
- [Joint stereo 3D object detection and implicit surface reconstruction](https://mlsanity.com/paper/2111.12924/) (2021)

## Abstract (arXiv)

Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. This is an ill-posed problem with a major difficulty lying in the information loss by depth-agnostic cameras. Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space. To improve the efficiency of sampling, we propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step. This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it. The proposed framework, Reinforced Axial Refinement Network (RAR-Net), serves as a post-processing stage which can be freely integrated into existing monocular 3D detection methods, and improve the performance on the KITTI dataset with small extra computational costs.