Search Results for author: Mohammad-Ali Nikouei Mahani

Found 4 papers, 0 papers with code

RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds

no code implementations1 Apr 2022 Ramy Battrawy, René Schuster, Mohammad-Ali Nikouei Mahani, Didier Stricker

The proposed RMS-FlowNet is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation which can operate on point clouds of high density.

Scene Flow Estimation

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

no code implementations28 Oct 2020 Stefano Gasperini, Mohammad-Ali Nikouei Mahani, Alvaro Marcos-Ramiro, Nassir Navab, Federico Tombari

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.

Clustering Instance Segmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.