Enregistré dans:
Détails bibliographiques
Auteurs principaux: Qiu, Di, Zhang, Yinda, Beeler, Thabo, Tankovich, Vladimir, Häne, Christian, Fanello, Sean, Rhemann, Christoph, Escolano, Sergio Orts
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2404.02225
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918007735844864
author Qiu, Di
Zhang, Yinda
Beeler, Thabo
Tankovich, Vladimir
Häne, Christian
Fanello, Sean
Rhemann, Christoph
Escolano, Sergio Orts
author_facet Qiu, Di
Zhang, Yinda
Beeler, Thabo
Tankovich, Vladimir
Häne, Christian
Fanello, Sean
Rhemann, Christoph
Escolano, Sergio Orts
contents We propose CHOSEN, a simple yet flexible, robust and effective multi-view depth refinement framework. It can be employed in any existing multi-view stereo pipeline, with straightforward generalization capability for different multi-view capture systems such as camera relative positioning and lenses. Given an initial depth estimation, CHOSEN iteratively re-samples and selects the best hypotheses, and automatically adapts to different metric or intrinsic scales determined by the capture system. The key to our approach is the application of contrastive learning in an appropriate solution space and a carefully designed hypothesis feature, based on which positive and negative hypotheses can be effectively distinguished. Integrated in a simple baseline multi-view stereo pipeline, CHOSEN delivers impressive quality in terms of depth and normal accuracy compared to many current deep learning based multi-view stereo pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02225
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CHOSEN: Contrastive Hypothesis Selection for Multi-View Depth Refinement
Qiu, Di
Zhang, Yinda
Beeler, Thabo
Tankovich, Vladimir
Häne, Christian
Fanello, Sean
Rhemann, Christoph
Escolano, Sergio Orts
Computer Vision and Pattern Recognition
Artificial Intelligence
We propose CHOSEN, a simple yet flexible, robust and effective multi-view depth refinement framework. It can be employed in any existing multi-view stereo pipeline, with straightforward generalization capability for different multi-view capture systems such as camera relative positioning and lenses. Given an initial depth estimation, CHOSEN iteratively re-samples and selects the best hypotheses, and automatically adapts to different metric or intrinsic scales determined by the capture system. The key to our approach is the application of contrastive learning in an appropriate solution space and a carefully designed hypothesis feature, based on which positive and negative hypotheses can be effectively distinguished. Integrated in a simple baseline multi-view stereo pipeline, CHOSEN delivers impressive quality in terms of depth and normal accuracy compared to many current deep learning based multi-view stereo pipelines.
title CHOSEN: Contrastive Hypothesis Selection for Multi-View Depth Refinement
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2404.02225