6D Object Pose Estimation With Color/Geometry Attention Fusion

Yuan, Honglin; Veltkamp, Remco C.

doi:10.1109/icarcv50220.2020.9305469

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It works under an iterative refinement framework like DeepIM [36] where the pose residuals are estimated from a network. A graph attention module was added after the feature extraction in [43] for the 6D pose estimation from RGB-D images.…”

Section: Related Workmentioning

confidence: 99%

CSA6D: Channel-Spatial Attention Networks for 6D Object Pose Estimation

Chen

2021

Cogn Comput

View full text Add to dashboard Cite

Abstract6D object pose estimation plays a crucial role in robotic manipulation and grasping tasks. The aim to estimate the 6D object pose from RGB or RGB-D images is to detect objects and estimate their orientations and translations relative to the given canonical models. RGB-D cameras provide two sensory modalities: RGB and depth images, which could benefit the estimation accuracy. But the exploitation of two different modality sources remains a challenging issue. In this paper, inspired by recent works on attention networks that could focus on important regions and ignore unnecessary information, we propose a novel network: Channel-Spatial Attention Network (CSA6D) to estimate the 6D object pose from RGB-D camera. The proposed CSA6D includes a pre-trained 2D network to segment the interested objects from RGB image. Then it uses two separate networks to extract appearance and geometrical features from RGB and depth images for each segmented object. Two feature vectors for each pixel are stacked together as a fusion vector which is refined by an attention module to generate a aggregated feature vector. The attention module includes a channel attention block and a spatial attention block which can effectively leverage the concatenated embeddings into accurate 6D pose prediction on known objects. We evaluate proposed network on two benchmark datasets YCB-Video dataset and LineMod dataset and the results show it can outperform previous state-of-the-art methods under ADD and ADD-S metrics. Also, the attention map demonstrates our proposed network searches for the unique geometry information as the most likely features for pose estimation. From experiments, we conclude that the proposed network can accurately estimate the object pose by effectively leveraging multi-modality features.

show abstract

Section: Related Workmentioning

confidence: 99%

CSA6D: Channel-Spatial Attention Networks for 6D Object Pose Estimation

Chen

2021

Cogn Comput

View full text Add to dashboard Cite

show abstract

6D Object Pose Estimation With Color/Geometry Attention Fusion

Cited by 1 publication

References 18 publications

CSA6D: Channel-Spatial Attention Networks for 6D Object Pose Estimation

CSA6D: Channel-Spatial Attention Networks for 6D Object Pose Estimation

Contact Info

Product

Resources

About