← Search

Mohammad-Ali Nikouei Mahani

3 accepted papers

2022

3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection

CVPR 2022poster

As 3D object detection on point clouds relies on the geometrical relationships between the points, non-standard object shapes can hinder a method's detection capability. However, in safety-critical settings, robustness to out-of-domain and long-tail samples is fundamental to circumvent dangerous iss…

Cited by 69PDFcodeScholar
2022

CertainNet: Sampling-Free Uncertainty Estimation for Object Detection

RA-L 2022

Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In perception for autonomous driving, measuring the uncertainty means providing additional calibrated information to downstream tasks, such as path planning, that can use it towards safe navigation.

Cited by 29SourceScholar
2021

Panoster: End-to-End Panoptic Segmentation of LiDAR Point Clouds

RA-L 2021

Panoptic segmentation has recently unified semantic and instance segmentation, previously addressed separately, thus taking a step further towards creating more comprehensive and efficient perception systems. In this letter, we present Panoster, a novel proposal-free panoptic segmentation method for

Cited by 76SourceScholar