MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation

03/23/2021
by   Hansheng Chen, et al.
0

Object localization in 3D space is a challenging aspect in monocular 3D object detection. Recent advances in 6DoF pose estimation have shown that predicting dense 2D-3D correspondence maps between image and object 3D model and then estimating object pose via Perspective-n-Point (PnP) algorithm can achieve remarkable localization accuracy. Yet these methods rely on training with ground truth of object geometry, which is difficult to acquire in real outdoor scenes. To address this issue, we propose MonoRUn, a novel detection framework that learns dense correspondences and geometry in a self-supervised manner, with simple 3D bounding box annotations. To regress the pixel-related 3D object coordinates, we employ a regional reconstruction network with uncertainty awareness. For self-supervised training, the predicted 3D coordinates are projected back to the image plane. A Robust KL loss is proposed to minimize the uncertainty-weighted reprojection error. During testing phase, we exploit the network uncertainty by propagating it through all downstream modules. More specifically, the uncertainty-driven PnP algorithm is leveraged to estimate object pose and its covariance. Extensive experiments demonstrate that our proposed approach outperforms current state-of-the-art methods on KITTI benchmark.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 7

page 9

page 10

page 11

research
09/30/2020

Monocular Differentiable Rendering for Self-Supervised 3D Object Detection

3D object detection from monocular images is an ill-posed problem due to...
research
06/23/2020

Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time

In this paper we propose a novel 3D single-shot object detection method ...
research
11/03/2022

Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection

The ground plane prior is a very informative geometry clue in monocular ...
research
04/29/2019

DeepHMap++: Combined Projection Grouping and Correspondence Learning for Full DoF Pose Estimation

In recent years, estimating the 6D pose of object instances with convolu...
research
04/14/2020

Self6D: Self-Supervised Monocular 6D Object Pose Estimation

Estimating the 6D object pose is a fundamental problem in computer visio...
research
10/20/2021

Robust Monocular Localization in Sparse HD Maps Leveraging Multi-Task Uncertainty Estimation

Robust localization in dense urban scenarios using a low-cost sensor set...
research
06/25/2022

Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes

Modern object detection architectures are moving towards employing self-...

Please sign up or login with your details

Forgot password? Click here to reset