A comprehensive review of modern object segmentation approaches

Y Wang, U Ahsan, H Li, M Hagen - Foundations and Trends® …, 2022 - nowpublishers.com
Image segmentation is the task of associating pixels in an image with their respective object
class labels. It has a wide range of applications in many industries including healthcare …

A survey on deep learning-based panoptic segmentation

X Li, D Chen - Digital Signal Processing, 2022 - Elsevier
In the era of deep learning, various segmentation tasks have been studied. As a new
segmentation task, panoptic segmentation has been proposed and studied by researchers …

[HTML][HTML] Kidney tumor semantic segmentation using deep learning: A survey of state-of-the-art

A Abdelrahman, S Viriri - Journal of imaging, 2022 - mdpi.com
Cure rates for kidney cancer vary according to stage and grade; hence, accurate diagnostic
procedures for early detection and diagnosis are crucial. Some difficulties with manual …

Panoptic-depth forecasting

JV Hurtado, R Mohan, A Valada - ar**
A Ciamarra, F Becattini, L Seidenari… - … Conference on Image …, 2022 - Springer
For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and
consequently predict imminent future scenarios to ensure safety to itself and others. This can …

Dense semantic forecasting in video by joint regression of features and feature motion

J Šarić, S Vražić, S Šegvić - IEEE Transactions on Neural …, 2021 - ieeexplore.ieee.org
Dense semantic forecasting anticipates future events in the video by inferring pixel-level
semantics of an unobserved future image. We present a novel approach that is applicable to …

Contour-based object forecasting for autonomous driving

J Jang, D Kim, D **, CS Kim - Journal of Visual Communication and Image …, 2025 - Elsevier
A novel algorithm, called contour-based object forecasting (COF), to simultaneously perform
contour-based segmentation and depth estimation of objects in future frames in autonomous …

Forecasting of depth and ego-motion with transformers and self-supervision

HE Boulahbal, A Voicila… - 2022 26th International …, 2022 - ieeexplore.ieee.org
This paper addresses the problem of end-to-end self-supervised forecasting of depth and
ego motion. Given a sequence of raw images, the aim is to forecast both the geometry and …

Low-latency LiDAR semantic segmentation

T Hori, T Yairi - 2022 IEEE/RSJ International Conference on …, 2022 - ieeexplore.ieee.org
Several methods of semantic segmentation using light detection and ranging (LiDAR)
sensors have been proposed for the recognition of surrounding objects by autonomous …