Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bethell, Adam, Garg, Ravi, Reid, Ian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929632673005568
author Bethell, Adam
Garg, Ravi
Reid, Ian
author_facet Bethell, Adam
Garg, Ravi
Reid, Ian
contents Estimating the 6D pose and 3D size of an object from an image is a fundamental task in computer vision. Most current approaches are restricted to specific instances with known models or require ground truth depth information or point cloud captures from LIDAR. We tackle the harder problem of pose estimation for category-level objects from a single RGB image. We propose a novel solution that eliminates the need for specific object models or depth information. Our method utilises score-based diffusion models to generate object pose hypotheses to model the distribution of possible poses for the object. Unlike previous methods that rely on costly trained likelihood estimators to remove outliers before pose aggregation using mean pooling, we introduce a simpler approach using Mean Shift to estimate the mode of the distribution as the final pose estimate. Our approach outperforms the current state-of-the-art on the REAL275 dataset by a significant margin.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11420
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusion
Bethell, Adam
Garg, Ravi
Reid, Ian
Computer Vision and Pattern Recognition
Estimating the 6D pose and 3D size of an object from an image is a fundamental task in computer vision. Most current approaches are restricted to specific instances with known models or require ground truth depth information or point cloud captures from LIDAR. We tackle the harder problem of pose estimation for category-level objects from a single RGB image. We propose a novel solution that eliminates the need for specific object models or depth information. Our method utilises score-based diffusion models to generate object pose hypotheses to model the distribution of possible poses for the object. Unlike previous methods that rely on costly trained likelihood estimators to remove outliers before pose aggregation using mean pooling, we introduce a simpler approach using Mean Shift to estimate the mode of the distribution as the final pose estimate. Our approach outperforms the current state-of-the-art on the REAL275 dataset by a significant margin.
title Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.11420