Probabilistic 3d regression with projected huber distribution
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 19 references that are in the map. First posted on arXiv 9 Mar 2023.
Builds on
13 of 19 references.
References · 13
- 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
- 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
- 2019Learnable Triangulation of Human Posecited by 160
- 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
- 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
- 2020LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihoodcited by 87
- 2016A Large Dataset of Object Scanscited by 64
- 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
- 2019MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimationcited by 39
- 2019Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Drivingcited by 30
- 2020HDNet: Human Depth Estimation for Multi-Person Camera-Space Localizationcited by 20
- 2021Probabilistic Regression with Huber Distributionscited by 2
1 more
Built on by
Not cited yet.