# Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking

arXiv: https://arxiv.org/abs/2206.03666 · HTML: https://mlsanity.com/paper/2206.03666/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 55 references that are in the map.
- First posted on arXiv 8 Jun 2022.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (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)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [Towards Real-Time Multi-Object Tracking](https://mlsanity.com/paper/1909.12605/) (2019)
- [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2012.10992/) (2020)
- [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://mlsanity.com/paper/1907.06038/) (2019)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [Disentangling Monocular 3D Object Detection](https://mlsanity.com/paper/1905.12365/) (2019)
- [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://mlsanity.com/paper/2002.10111/) (2020)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [On the uncertainty of self-supervised monocular depth estimation](https://mlsanity.com/paper/2005.06209/) (2020)
- [Flow-Guided Feature Aggregation for Video Object Detection](https://mlsanity.com/paper/1703.10025/) (2017)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships](https://mlsanity.com/paper/2003.00504/) (2020)
- [RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving](https://mlsanity.com/paper/2001.03343/) (2020)
- [Audiovisual SlowFast Networks for Video Recognition](https://mlsanity.com/paper/2001.08740/) (2020)

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

- [Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection](https://mlsanity.com/paper/2210.02443/) (2022)
- [Monocular Depth Estimation using Diffusion Models](https://mlsanity.com/paper/2302.14816/) (2023)
- [STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation](https://mlsanity.com/paper/2302.01334/) (2023)
- [NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization](https://mlsanity.com/paper/2305.17763/) (2023)
- [3D Multiple Object Tracking on Autonomous Driving: A Literature Review](https://mlsanity.com/paper/2309.15411/) (2023)
- [You Only Look Bottom-Up for Monocular 3D Object Detection](https://mlsanity.com/paper/2401.15319/) (2024)
- [Robust Inverse Graphics via Probabilistic Inference](https://mlsanity.com/paper/2402.01915/) (2024)
- [Compass: A Decentralized Scheduler for Latency-Sensitive ML Workflows](https://mlsanity.com/paper/2402.17652/) (2024)
- [Enhanced Object Tracking by Self-Supervised Auxiliary Depth Estimation Learning](https://mlsanity.com/paper/2405.14195/) (2024)

## Abstract (arXiv)

Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior performance when compared to LiDAR-based techniques. Through systematic analysis, we identified that per-object depth estimation accuracy is a major factor bounding the performance. Motivated by this observation, we propose a multi-level fusion method that combines different representations (RGB and pseudo-LiDAR) and temporal information across multiple frames for objects (tracklets) to enhance per-object depth estimation. Our proposed fusion method achieves the state-of-the-art performance of per-object depth estimation on the Waymo Open Dataset, the KITTI detection dataset, and the KITTI MOT dataset. We further demonstrate that by simply replacing estimated depth with fusion-enhanced depth, we can achieve significant improvements in monocular 3D perception tasks, including detection and tracking.