FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

He, Yisheng; Huang, Haibin; Fan, Haoqiang; Chen, Qifeng; Sun, Jian

doi:10.1109/cvpr46437.2021.00302

Cited by 173 publications

(74 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we surveyed the state of the art of 6D object detection with a focus on industrial applications for which we identified model-based training and support for RGBD images as being especially important. We presented a collection of qualitative and quantitative information on object detectors from the literature and new data for the object detector FFB6D [ 2 ]. These data were discussed, and promising candidates for taking on specific challenges of industrial applications were identified.…”

Section: Discussionmentioning

confidence: 99%

“…The learning-based method FFB6D [ 2 ] was trained on synthetic images by ourselves. To train FFB6D, we used the synthetical images generated with BlenderProc [ 4 ] for BOP Challenge 2020 [ 3 ], using scene 2 as the validation set.…”

Section: Methodsmentioning

confidence: 99%

“…He et al [ 34 ] presented PVN3D, a network relying on keypoint detection and Hough voting, building on the DenseFusion features by Wang et al [ 35 ]. They expanded this work in 2020 with bidirectional fusion of RGB- and depth-features, calling the resulting method FFB6D [ 2 ]. SurfEmb by Haugaard and Buch [ 36 ] introduces a contrastive loss.…”

Section: Related Workmentioning

confidence: 99%

“… A comprehensive collection of empirical data from experiments with 6D object detectors that meet the identified criteria. Empirical data on the performance of the object detector FFB6D [ 2 ], which has not been evaluated with purely model-based training, yet. …”

Section: Introductionmentioning

confidence: 99%

“…Empirical data on the performance of the object detector FFB6D [ 2 ], which has not been evaluated with purely model-based training, yet.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Survey of 6D Object Detection Based on 3D Models for Industrial Applications

2022

View full text Add to dashboard Cite

Six-dimensional object detection of rigid objects is a problem especially relevant for quality control and robotic manipulation in industrial contexts. This work is a survey of the state of the art of 6D object detection with these use cases in mind, specifically focusing on algorithms trained only with 3D models or renderings thereof. Our first contribution is a listing of requirements typically encountered in industrial applications. The second contribution is a collection of quantitative evaluation results for several different 6D object detection methods trained with synthetic data and the comparison and analysis thereof. We identify the top methods for individual requirements that industrial applications have for object detectors, but find that a lack of comparable data prevents large-scale comparison over multiple aspects.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Empirical data on the performance of the object detector FFB6D [ 2 ], which has not been evaluated with purely model-based training, yet.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Survey of 6D Object Detection Based on 3D Models for Industrial Applications

2022

View full text Add to dashboard Cite

show abstract

A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking

Stoiber

Pfanne

Strobl

et al. 2021

Computer Vision – ACCV 2020

View full text Add to dashboard Cite

In many applications of advanced robotic manipulation, six degrees of freedom (6DoF) object pose estimates are continuously required. In this work, we develop a multimodality tracker that fuses information from visual appearance and geometry to estimate object poses. The algorithm extends our previous method ICG, which uses geometry, to additionally consider surface appearance. In general, object surfaces contain local characteristics from text, graphics, and patterns, as well as global differences from distinct materials and colors. To incorporate this visual information, two modalities are developed. For local characteristics, keypoint features are used to minimize distances between points from keyframes and the current image. For global differences, a novel region approach is developed that considers multiple regions on the object surface. In addition, it allows the modeling of external geometries. Experiments on the YCB-Video and OPT datasets demonstrate that our approach ICG+ performs best on both datasets, outperforming both conventional and deep learningbased methods. At the same time, the algorithm is highly efficient and runs at more than 300 Hz. The source code of our tracker is publicly available.

show abstract

RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation

Zhang

Lou

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

Cited by 173 publications

References 55 publications

A Survey of 6D Object Detection Based on 3D Models for Industrial Applications

A Survey of 6D Object Detection Based on 3D Models for Industrial Applications

A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking

RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation

Contact Info

Product

Resources

About