NeRF-Feat: 6D Object Pose Estimation using Feature Rendering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Vutukur, Shishir Reddy, Brock, Heike, Busam, Benjamin, Birdal, Tolga, Hutter, Andreas, Ilic, Slobodan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910495366184960
author Vutukur, Shishir Reddy
Brock, Heike
Busam, Benjamin
Birdal, Tolga
Hutter, Andreas
Ilic, Slobodan
author_facet Vutukur, Shishir Reddy
Brock, Heike
Busam, Benjamin
Birdal, Tolga
Hutter, Andreas
Ilic, Slobodan
contents Object Pose Estimation is a crucial component in robotic grasping and augmented reality. Learning based approaches typically require training data from a highly accurate CAD model or labeled training data acquired using a complex setup. We address this by learning to estimate pose from weakly labeled data without a known CAD model. We propose to use a NeRF to learn object shape implicitly which is later used to learn view-invariant features in conjunction with CNN using a contrastive loss. While NeRF helps in learning features that are view-consistent, CNN ensures that the learned features respect symmetry. During inference, CNN is used to predict view-invariant features which can be used to establish correspondences with the implicit 3d model in NeRF. The correspondences are then used to estimate the pose in the reference frame of NeRF. Our approach can also handle symmetric objects unlike other approaches using a similar training setup. Specifically, we learn viewpoint invariant, discriminative features using NeRF which are later used for pose estimation. We evaluated our approach on LM, LM-Occlusion, and T-Less dataset and achieved benchmark accuracy despite using weakly labeled data.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13796
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NeRF-Feat: 6D Object Pose Estimation using Feature Rendering
Vutukur, Shishir Reddy
Brock, Heike
Busam, Benjamin
Birdal, Tolga
Hutter, Andreas
Ilic, Slobodan
Computer Vision and Pattern Recognition
Object Pose Estimation is a crucial component in robotic grasping and augmented reality. Learning based approaches typically require training data from a highly accurate CAD model or labeled training data acquired using a complex setup. We address this by learning to estimate pose from weakly labeled data without a known CAD model. We propose to use a NeRF to learn object shape implicitly which is later used to learn view-invariant features in conjunction with CNN using a contrastive loss. While NeRF helps in learning features that are view-consistent, CNN ensures that the learned features respect symmetry. During inference, CNN is used to predict view-invariant features which can be used to establish correspondences with the implicit 3d model in NeRF. The correspondences are then used to estimate the pose in the reference frame of NeRF. Our approach can also handle symmetric objects unlike other approaches using a similar training setup. Specifically, we learn viewpoint invariant, discriminative features using NeRF which are later used for pose estimation. We evaluated our approach on LM, LM-Occlusion, and T-Less dataset and achieved benchmark accuracy despite using weakly labeled data.
title NeRF-Feat: 6D Object Pose Estimation using Feature Rendering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.13796