HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Pose Dataset with Household Objects in Realistic Scenarios

Jung, Hyunjun; Wu, Shun-Cheng; Ruhkamp, Patrick; Zhai, Guangyao; Schieber, Hannah; Rizzoli, Giulia; Wang, Pengyuan; Zhao, Haixing; Garattoni, Lorenzo; Meier, Sven; Roth, Daniel; Navab, Nassir; Busam, Benjamin

doi:10.48550/arxiv.2212.10428

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a model-based approach that utilizes object model projections on synthetic and real datasets to train networks to detect object poses [ 30 ]. However, most existing datasets for pose estimation rely on RGB-D data rather than binocular vision [ 31 ]. Furthermore, while there have been studies exploring the use of infrared (IR) stereo imaging for vegetable classification [ 32 ], the available stereo benchmark datasets primarily consist of RGB imagery and lack object size information.…”

Section: Related Workmentioning

confidence: 99%

A Variable Photo-Model Method for Object Pose and Size Estimation with Stereo Vision in a Complex Home Scene

Tian

Wang

2023

Sensors

View full text Add to dashboard Cite

Model-based stereo vision methods can estimate the 6D poses of rigid objects. They can help robots to achieve a target grip in complex home environments. This study presents a novel approach, called the variable photo-model method, to estimate the pose and size of an unknown object using a single photo of the same category. By employing a pre-trained You Only Look Once (YOLO) v4 weight for object detection and 2D model generation in the photo, the method converts the segmented 2D photo-model into 3D flat photo-models assuming different sizes and poses. Through perspective projection and model matching, the method finds the best match between the model and the actual object in the captured stereo images. The matching fitness function is optimized using a genetic algorithm (GA). Unlike data-driven approaches, this approach does not require multiple photos or pre-training time for single object pose recognition, making it more versatile. Indoor experiments demonstrate the effectiveness of the variable photo-model method in estimating the pose and size of the target objects within the same class. The findings of this study have practical implications for object detection prior to robotic grasping, particularly due to its ease of application and the limited data required.

show abstract

Section: Related Workmentioning

confidence: 99%

A Variable Photo-Model Method for Object Pose and Size Estimation with Stereo Vision in a Complex Home Scene

Tian

Wang

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…However, it contains significantly more occlusions, and some objects in unconstrained poses. The recently released House- Cat6D [77] is a follow-up dataset, that significantly improves with regards to limited viewpoints. Finally, the Wild6D dataset [50] is a largescale dataset for self-supervised learning.…”

Section: Datasetsmentioning

confidence: 99%

“…See text for further explanation and discussion. Annotations for Redwood dataset[4]; objects freely rotated in hands HouseCat6D[77] 194 41 10 Larger dataset following PhoCaL[76]; better viewpoint coverage…”

mentioning

confidence: 99%

RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluation

Bruns¹

2023

Preprint

View full text Add to dashboard Cite

Recently, various methods for 6D pose and shape estimation of objects at a per-category level have been proposed. This work provides an overview of the field in terms of methods, datasets, and evaluation protocols. First, an overview of existing works and their commonalities and differences is provided. Second, we take a critical look at the predominant evaluation protocol, including metrics and datasets. Based on the findings, we propose a new set of metrics, contribute new annotations for the Redwood dataset, and evaluate state-of-the-art methods in a fair comparison. The results indicate that existing methods do not generalize well to unconstrained orientations and are actually heavily biased towards objects being upright. We provide an easy-to-use evaluation toolbox with well-defined metrics, methods, and dataset interfaces, which allows evaluation and comparison with various state-of-the-art approaches (https://github.com/roym899/pose and shape evaluation).

show abstract

HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Pose Dataset with Household Objects in Realistic Scenarios

Cited by 2 publications

References 0 publications

A Variable Photo-Model Method for Object Pose and Size Estimation with Stereo Vision in a Complex Home Scene

A Variable Photo-Model Method for Object Pose and Size Estimation with Stereo Vision in a Complex Home Scene

RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluation

Contact Info

Product

Resources

About