Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Jianzheng, Mo, Xianyu, Liu, Ziling, Yang, Jinyu, Zheng, Feng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.12944
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910878604984320
author Huang, Jianzheng
Mo, Xianyu
Liu, Ziling
Yang, Jinyu
Zheng, Feng
author_facet Huang, Jianzheng
Mo, Xianyu
Liu, Ziling
Yang, Jinyu
Zheng, Feng
contents Point tracking is becoming a powerful solver for motion estimation and video editing. Compared to classical feature matching, point tracking methods have the key advantage of robustly tracking points under complex camera motion trajectories and over extended periods. However, despite certain improvements in methodologies, current point tracking methods still struggle to track any position in video frames, especially in areas that are texture-less or weakly textured. In this work, we first introduce metrics for evaluating the texture intensity of a 3D object. Using these metrics, we classify the 3D models in ShapeNet into three levels of texture intensity and create GIFT, a challenging synthetic benchmark comprising 1800 indoor video sequences with rich annotations. Unlike existing datasets that assign ground truth points arbitrarily, GIFT precisely anchors ground truth on classified target objects, ensuring that each video corresponds to a specific texture intensity level. Furthermore, we comprehensively evaluate current methods on GIFT to assess their performance across different texture intensity levels and analyze the impact of texture on point tracking.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12944
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GIFT: Generated Indoor video frames for Texture-less point tracking
Huang, Jianzheng
Mo, Xianyu
Liu, Ziling
Yang, Jinyu
Zheng, Feng
Computer Vision and Pattern Recognition
Point tracking is becoming a powerful solver for motion estimation and video editing. Compared to classical feature matching, point tracking methods have the key advantage of robustly tracking points under complex camera motion trajectories and over extended periods. However, despite certain improvements in methodologies, current point tracking methods still struggle to track any position in video frames, especially in areas that are texture-less or weakly textured. In this work, we first introduce metrics for evaluating the texture intensity of a 3D object. Using these metrics, we classify the 3D models in ShapeNet into three levels of texture intensity and create GIFT, a challenging synthetic benchmark comprising 1800 indoor video sequences with rich annotations. Unlike existing datasets that assign ground truth points arbitrarily, GIFT precisely anchors ground truth on classified target objects, ensuring that each video corresponds to a specific texture intensity level. Furthermore, we comprehensively evaluate current methods on GIFT to assess their performance across different texture intensity levels and analyze the impact of texture on point tracking.
title GIFT: Generated Indoor video frames for Texture-less point tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.12944