# Probabilistic 3d regression with projected huber distribution

arXiv: https://arxiv.org/abs/2303.05245 · HTML: https://mlsanity.com/paper/2303.05245/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 13 of 13)

- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving](https://mlsanity.com/paper/1903.08701/) (2019)
- [Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1907.11346/) (2019)
- [LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood](https://mlsanity.com/paper/2004.02980/) (2020)
- [A Large Dataset of Object Scans](https://mlsanity.com/paper/1602.02481/) (2016)
- [SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation](https://mlsanity.com/paper/2008.11469/) (2020)
- [MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation](https://mlsanity.com/paper/1906.06059/) (2019)
- [Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving](https://mlsanity.com/paper/1909.12358/) (2019)
- [HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization](https://mlsanity.com/paper/2007.08943/) (2020)
- [Probabilistic Regression with Huber Distributions](https://mlsanity.com/paper/2111.10296/) (2021)
- [On the Evaluation of RGB-D-based Categorical Pose and Shape Estimation](https://mlsanity.com/paper/2202.10346/) (2022)

## Abstract (arXiv)

Estimating probability distributions which describe where an object is likely to be from camera data is a task with many applications. In this work we describe properties which we argue such methods should conform to. We also design a method which conform to these properties. In our experiments we show that our method produces uncertainties which correlate well with empirical errors. We also show that the mode of the predicted distribution outperform our regression baselines. The code for our implementation is available online.