# Geometry-based Distance Decomposition for Monocular 3D Object Detection

arXiv: https://arxiv.org/abs/2104.03775 · HTML: https://mlsanity.com/paper/2104.03775/

## Key facts

- Cited by 84 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 8 Apr 2021.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://mlsanity.com/paper/1907.06038/) (2019)
- [Disentangling Monocular 3D Object Detection](https://mlsanity.com/paper/1905.12365/) (2019)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019)

## Built on by (most cited first, 30 of 84)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer](https://mlsanity.com/paper/2203.10981/) (2022)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection](https://mlsanity.com/paper/2203.13310/) (2022)
- [MonoDistill: Learning Spatial Features for Monocular 3D Object Detection](https://mlsanity.com/paper/2201.10830/) (2022)
- [Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection](https://mlsanity.com/paper/2112.04628/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2112.11088/) (2021)
- [DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.10758/) (2022)
- [Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2211.07171/) (2022)
- [Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection](https://mlsanity.com/paper/2205.09373/) (2022)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.08531/) (2022)
- [MonoCD: Monocular 3D Object Detection with Complementary Depths](https://mlsanity.com/paper/2404.03181/) (2024)
- [Monocular 3D Object Detection with Depth from Motion](https://mlsanity.com/paper/2207.12988/) (2022)
- [MonoGround: Detecting Monocular 3D Objects from the Ground](https://mlsanity.com/paper/2206.07372/) (2022)
- [Learning Occupancy for Monocular 3D Object Detection](https://mlsanity.com/paper/2305.15694/) (2023)
- [Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection](https://mlsanity.com/paper/2204.11582/) (2022)
- [MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection](https://mlsanity.com/paper/2308.09421/) (2023)
- [Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2203.02112/) (2022)
- [MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection](https://mlsanity.com/paper/2203.08563/) (2022)
- [Lidar Point Cloud Guided Monocular 3D Object Detection](https://mlsanity.com/paper/2104.09035/) (2021)
- [Densely Constrained Depth Estimator for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.10047/) (2022)
- [TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM](https://mlsanity.com/paper/2210.16204/) (2022)
- [Homography Loss for Monocular 3D Object Detection](https://mlsanity.com/paper/2204.00754/) (2022)
- [OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection](https://mlsanity.com/paper/2211.01142/) (2022)
- [Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.04448/) (2022)
- [Aerial Monocular 3D Object Detection](https://mlsanity.com/paper/2208.03974/) (2022)
- [Boosting 3D Object Detection by Simulating Multimodality on Point Clouds](https://mlsanity.com/paper/2206.14971/) (2022)

## Abstract (arXiv)

Monocular 3D object detection is of great significance for autonomous driving but remains challenging. The core challenge is to predict the distance of objects in the absence of explicit depth information. Unlike regressing the distance as a single variable in most existing methods, we propose a novel geometry-based distance decomposition to recover the distance by its factors. The decomposition factors the distance of objects into the most representative and stable variables, i.e. the physical height and the projected visual height in the image plane. Moreover, the decomposition maintains the self-consistency between the two heights, leading to robust distance prediction when both predicted heights are inaccurate. The decomposition also enables us to trace the causes of the distance uncertainty for different scenarios. Such decomposition makes the distance prediction interpretable, accurate, and robust. Our method directly predicts 3D bounding boxes from RGB images with a compact architecture, making the training and inference simple and efficient. The experimental results show that our method achieves the state-of-the-art performance on the monocular 3D Object Detection and Birds Eye View tasks of the KITTI dataset, and can generalize to images with different camera intrinsics.