DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

07/21/2022
by   Abhinav Kumar, et al.
5

Modern neural networks use building blocks such as convolutions that are equivariant to arbitrary 2D translations. However, these vanilla blocks are not equivariant to arbitrary 3D translations in the projective manifold. Even then, all monocular 3D detectors use vanilla blocks to obtain the 3D coordinates, a task for which the vanilla blocks are not designed for. This paper takes the first step towards convolutions equivariant to arbitrary 3D translations in the projective manifold. Since the depth is the hardest to estimate for monocular detection, this paper proposes Depth EquiVarIAnt NeTwork (DEVIANT) built with existing scale equivariant steerable blocks. As a result, DEVIANT is equivariant to the depth translations in the projective manifold whereas vanilla networks are not. The additional depth equivariance forces the DEVIANT to learn consistent depth estimates, and therefore, DEVIANT achieves state-of-the-art monocular 3D detection results on KITTI and Waymo datasets in the image-only category and performs competitively to methods using extra information. Moreover, DEVIANT works better than vanilla networks in cross-dataset evaluation. Code and models at https://github.com/abhi1kumar/DEVIANT

READ FULL TEXT

page 38

page 40

page 41

page 42

research
03/21/2022

MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer

Monocular 3D object detection is an important yet challenging task in au...
research
03/24/2022

MonoDETR: Depth-aware Transformer for Monocular 3D Object Detection

Monocular 3D object detection has long been a challenging task in autono...
research
03/31/2021

GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection

Modern 3D object detectors have immensely benefited from the end-to-end ...
research
03/30/2021

Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection

The objective of this paper is to learn context- and depth-aware feature...
research
08/25/2021

AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection

Existing deep learning-based approaches for monocular 3D object detectio...
research
07/18/2022

DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection

Monocular 3D detection has drawn much attention from the community due t...
research
09/02/2023

S^3-MonoDETR: Supervised Shape Scale-perceptive Deformable Transformer for Monocular 3D Object Detection

Recently, transformer-based methods have shown exceptional performance i...

Please sign up or login with your details

Forgot password? Click here to reset