Guardado en:
Detalles Bibliográficos
Autores principales: Demler, Ilona, Chauhan, Saumya, Gkioxari, Georgia
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.19819
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918165810774016
author Demler, Ilona
Chauhan, Saumya
Gkioxari, Georgia
author_facet Demler, Ilona
Chauhan, Saumya
Gkioxari, Georgia
contents We introduce ITTO, a challenging new benchmark suite for evaluating and diagnosing the capabilities and limitations of point tracking methods. Our videos are sourced from existing datasets and egocentric real-world recordings, with high-quality human annotations collected through a multi-stage pipeline. ITTO captures the motion complexity, occlusion patterns, and object diversity characteristic of real-world scenes -- factors that are largely absent in current benchmarks. We conduct a rigorous analysis of state-of-the-art tracking methods on ITTO, breaking down performance along key axes of motion complexity. Our findings reveal that existing trackers struggle with these challenges, particularly in re-identifying points after occlusion, highlighting critical failure modes. These results point to the need for new modeling approaches tailored to real-world dynamics. We envision ITTO as a foundation testbed for advancing point tracking and guiding the development of more robust tracking algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19819
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Is This Tracker On? A Benchmark Protocol for Dynamic Tracking
Demler, Ilona
Chauhan, Saumya
Gkioxari, Georgia
Computer Vision and Pattern Recognition
We introduce ITTO, a challenging new benchmark suite for evaluating and diagnosing the capabilities and limitations of point tracking methods. Our videos are sourced from existing datasets and egocentric real-world recordings, with high-quality human annotations collected through a multi-stage pipeline. ITTO captures the motion complexity, occlusion patterns, and object diversity characteristic of real-world scenes -- factors that are largely absent in current benchmarks. We conduct a rigorous analysis of state-of-the-art tracking methods on ITTO, breaking down performance along key axes of motion complexity. Our findings reveal that existing trackers struggle with these challenges, particularly in re-identifying points after occlusion, highlighting critical failure modes. These results point to the need for new modeling approaches tailored to real-world dynamics. We envision ITTO as a foundation testbed for advancing point tracking and guiding the development of more robust tracking algorithms.
title Is This Tracker On? A Benchmark Protocol for Dynamic Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.19819