Salvato in:
Dettagli Bibliografici
Autori principali: Kaul, Sanchit, Luna, Joseph, Arora, Shray
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.05362
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909945749831680
author Kaul, Sanchit
Luna, Joseph
Arora, Shray
author_facet Kaul, Sanchit
Luna, Joseph
Arora, Shray
contents Lifting Structure-from-Motion (SfM) information from sequential and non-sequential image data is a time-consuming and computationally expensive task. In addition to this, the majority of publicly available data is unfit for processing due to inadequate camera pose variation, obscuring scene elements, and noisy data. To solve this problem, we introduce PoolNet, a versatile deep learning framework for frame-level and scene-level validation of in-the-wild data. We demonstrate that our model successfully differentiates SfM ready scenes from those unfit for processing while significantly undercutting the amount of time state of the art algorithms take to obtain structure-from-motion data.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05362
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PoolNet: Deep Learning for 2D to 3D Video Process Validation
Kaul, Sanchit
Luna, Joseph
Arora, Shray
Computer Vision and Pattern Recognition
Machine Learning
Lifting Structure-from-Motion (SfM) information from sequential and non-sequential image data is a time-consuming and computationally expensive task. In addition to this, the majority of publicly available data is unfit for processing due to inadequate camera pose variation, obscuring scene elements, and noisy data. To solve this problem, we introduce PoolNet, a versatile deep learning framework for frame-level and scene-level validation of in-the-wild data. We demonstrate that our model successfully differentiates SfM ready scenes from those unfit for processing while significantly undercutting the amount of time state of the art algorithms take to obtain structure-from-motion data.
title PoolNet: Deep Learning for 2D to 3D Video Process Validation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2512.05362