# MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation

arXiv: https://arxiv.org/abs/1906.06059 · HTML: https://mlsanity.com/paper/1906.06059/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2019.

## Built on by (most cited first, 30 of 39)

- [Geometry-based Distance Decomposition for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.03775/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications](https://mlsanity.com/paper/2111.01968/) (2021)
- [Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks](https://mlsanity.com/paper/2104.01797/) (2021)
- [Generalizable Multi-Camera 3D Pedestrian Detection](https://mlsanity.com/paper/2104.05813/) (2021)
- [Dual networks based 3D Multi-Person Pose Estimation from Monocular Video](https://mlsanity.com/paper/2205.00748/) (2022)
- [TrackFlow: Multi-Object Tracking with Normalizing Flows](https://mlsanity.com/paper/2308.11513/) (2023)
- [Toward Reliable Human Pose Forecasting with Uncertainty](https://mlsanity.com/paper/2304.06707/) (2023)
- [VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation](https://mlsanity.com/paper/2210.06028/) (2022)
- [Single View Physical Distance Estimation using Human Pose](https://mlsanity.com/paper/2106.10335/) (2021)
- [Do Pedestrians Pay Attention? Eye Contact Detection in the Wild](https://mlsanity.com/paper/2112.04212/) (2021)
- [From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration](https://mlsanity.com/paper/2212.09298/) (2022)
- [Unified Human Localization and Trajectory Prediction with Monocular Vision](https://mlsanity.com/paper/2503.03535/) (2025)
- [View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements](https://mlsanity.com/paper/2111.05060/) (2021)
- [TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression](https://mlsanity.com/paper/2310.18953/) (2023)
- [ViewBirdiformer: Learning to recover ground-plane crowd trajectories and ego-motion from a single ego-centric view](https://mlsanity.com/paper/2210.06332/) (2022)
- [Pedestrian Trajectory Forecasting Using Deep Ensembles Under Sensing Uncertainty](https://mlsanity.com/paper/2305.16620/) (2023)
- [HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformer](https://mlsanity.com/paper/2503.10777/) (2025)
- [People Tracking in Panoramic Video for Guiding Robots](https://mlsanity.com/paper/2206.02735/) (2022)
- [SpotNet: An Image Centric, Lidar Anchored Approach To Long Range Perception](https://mlsanity.com/paper/2405.15843/) (2024)
- [Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression](https://mlsanity.com/paper/2502.10587/) (2025)
- [Fast and Reliable Probabilistic Face Embeddings in the Wild](https://mlsanity.com/paper/2102.04075/) (2021)
- [Context Aware Object Geotagging](https://mlsanity.com/paper/2108.06302/) (2021)
- [InCrowdFormer: On-Ground Pedestrian World Model From Egocentric Views](https://mlsanity.com/paper/2303.09534/) (2023)
- [LaksNet: an end-to-end deep learning model for self-driving cars in Udacity simulator](https://mlsanity.com/paper/2310.16103/) (2023)
- [Monocular Per-Object Distance Estimation with Masked Object Modeling](https://mlsanity.com/paper/2401.03191/) (2024)
- [Bio-inspired visual relative localization for large swarms of UAVs](https://mlsanity.com/paper/2412.02393/) (2024)
- [Monocular Person Localization under Camera Ego-motion](https://mlsanity.com/paper/2503.02916/) (2025)
- [Logic-Guided Socially-aware Robot Navigation World Model](https://mlsanity.com/paper/2510.23509/) (2025)
- [Unsupervised Embedding Learning from Uncertainty Momentum Modeling](https://mlsanity.com/paper/2107.08892/) (2021)

## Abstract (arXiv)

We tackle the fundamentally ill-posed problem of 3D human localization from monocular RGB images. Driven by the limitation of neural networks outputting point estimates, we address the ambiguity in the task by predicting confidence intervals through a loss function based on the Laplace distribution. Our architecture is a light-weight feed-forward neural network that predicts 3D locations and corresponding confidence intervals given 2D human poses. The design is particularly well suited for small training data, cross-dataset generalization, and real-time applications. Our experiments show that we (i) outperform state-of-the-art results on KITTI and nuScenes datasets, (ii) even outperform a stereo-based method for far-away pedestrians, and (iii) estimate meaningful confidence intervals. We further share insights on our model of uncertainty in cases of limited observations and out-of-distribution samples.