# CARLA Drone: Monocular 3D Object Detection from a Different Perspective

arXiv: https://arxiv.org/abs/2408.11958 · HTML: https://mlsanity.com/paper/2408.11958/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 60 references that are in the map.
- First posted on arXiv 21 Aug 2024.

## Builds on (most cited first, 30 of 48)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [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)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection](https://mlsanity.com/paper/2204.05575/) (2022)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://mlsanity.com/paper/1907.06038/) (2019)
- [The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking](https://mlsanity.com/paper/1804.00518/) (2018)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild](https://mlsanity.com/paper/2207.10660/) (2022)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning](https://mlsanity.com/paper/2003.02437/) (2020)
- [Self-supervised Augmentation Consistency for Adapting Semantic Segmentation](https://mlsanity.com/paper/2105.00097/) (2021)
- [Delving into Localization Errors for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16237/) (2021)
- [Kinematic 3D Object Detection in Monocular Video](https://mlsanity.com/paper/2007.09548/) (2020)
- [Rethinking Pseudo-LiDAR Representation](https://mlsanity.com/paper/2008.04582/) (2020)
- [Geometry-based Distance Decomposition for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.03775/) (2021)
- [Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task](https://mlsanity.com/paper/2203.13608/) (2022)
- [BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection](https://mlsanity.com/paper/2303.08498/) (2023)
- [Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection](https://mlsanity.com/paper/2112.04628/) (2021)
- [Progressive Coordinate Transforms for Monocular 3D Object Detection](https://mlsanity.com/paper/2108.05793/) (2021)
- [Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection](https://mlsanity.com/paper/2205.09373/) (2022)

## Built on by (most cited first, 12 of 12)

- [Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset](https://mlsanity.com/paper/2504.17371/) (2025)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models](https://mlsanity.com/paper/2503.13743/) (2025)
- [IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection](https://mlsanity.com/paper/2511.19301/) (2025)
- [UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks](https://mlsanity.com/paper/2510.16923/) (2025)
- [LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection](https://mlsanity.com/paper/2512.05663/) (2025)
- [HetroD: A High-Fidelity Drone Dataset and Benchmark for Autonomous Driving in Heterogeneous Traffic](https://mlsanity.com/paper/2602.03447/) (2026)
- [SegFly: A Dataset and 2D-3D-2D Paradigm for Aerial RGB-Thermal Semantic Segmentation at Scale](https://mlsanity.com/paper/2603.17920/) (2026)
- [3DRot: Rediscovering the Missing Primitive for RGB-Based 3D Augmentation](https://mlsanity.com/paper/2508.01423/) (2025)
- [CAMF-Det: Closure-Aware Multimodal Fusion for LiDAR-Camera 3D Object Detection on UAV Platforms](https://mlsanity.com/paper/2606.09143/) (2026)
- [Co-GLANCE: Uncertainty-Aware Active Perception for Heterogeneous Robot Teaming](https://mlsanity.com/paper/2606.09919/) (2026)
- [MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection](https://mlsanity.com/paper/2608.14282/) (2026)

## Abstract (arXiv)

Existing techniques for monocular 3D detection have a serious restriction. They tend to perform well only on a limited set of benchmarks, faring well either on ego-centric car views or on traffic camera views, but rarely on both. To encourage progress, this work advocates for an extended evaluation of 3D detection frameworks across different camera perspectives. We make two key contributions. First, we introduce the CARLA Drone dataset, CDrone. Simulating drone views, it substantially expands the diversity of camera perspectives in existing benchmarks. Despite its synthetic nature, CDrone represents a real-world challenge. To show this, we confirm that previous techniques struggle to perform well both on CDrone and a real-world 3D drone dataset. Second, we develop an effective data augmentation pipeline called GroundMix. Its distinguishing element is the use of the ground for creating 3D-consistent augmentation of a training image. GroundMix significantly boosts the detection accuracy of a lightweight one-stage detector. In our expanded evaluation, we achieve the average precision on par with or substantially higher than the previous state of the art across all tested datasets.