Home | Publications | Sei25

Dynamic Vision: From 2D Multi-Object to 3D Point Tracking

MCML Authors

Abstract

Dynamic Vision, the processing of 2D and 3D spatio-temporal data such as video or LiDAR point cloud streams, is fundamental to various applications, including smart manufacturing, autonomous systems, and mixed reality. Recently, the field has significantly improved in tasks such as tracking at various granularities, from object- to particle-scale. Many approaches integrate appearance, semantic, and motion cues to enhance performance. We introduce key concepts of Dynamic Vision before analyzing the strengths of different cues across tasks of varying granularities.

phdthesis Sei25


Dissertation

TU München. Sep. 2025

Authors

J. Seidenschwarz

Links

URL

Research Area

 B1 | Computer Vision

BibTeXKey: Sei25

Back to Top