Real-Time Seamless Single Shot 6D Object Pose Prediction

Tekin, Bugra; Sinha, Sudipta N.; Fua, Pascal

doi:10.1109/cvpr.2018.00038

Cited by 715 publications

(555 citation statements)

References 40 publications

Supporting

Mentioning

546

Contrasting

Order By: Relevance

“…• We use 89 views on the upper hemisphere around the object, (a) LINEMOD [5] (b) "Single shot pose" [15] (c) Ground truth Figure 8: Qualitative results for on-the-fly surface color reconstructions of the "driller" object in relation to different pose detection methods. • For each view there are 7 in-plane rotations with roll angles between −45 • and 45 • .…”

Section: Discussionmentioning

confidence: 99%

“…To evaluate the applicability of our method for on-the-fly texturing with noisy pose data, we additionally used the state-of-the-art "single shot pose" (SSP) detector [15] instead of relying on groundtruth poses. Figure 8 shows qualitative results of texturing using groundtruth, SSP and LINEMOD poses.…”

Section: Using Noisy Pose Datamentioning

confidence: 99%

“…In recent years there has been great progress on the task of object detection and 6D pose estimation by means of convolutional neural networks (CNN) [15,7]. Combined with a successive local refinement method [10,14], it is now possible to obtain a precise object pose from a single RGB image only.…”

Section: Introductionmentioning

confidence: 99%

“…Even though this no longer provides state-of-the-art detection performance [15,7], the internal separation allows computing the DOT features on CAD geometry only and add the surface color at run-time. This is generally not possible with deep learning based approaches, which rely on surface color being available during training.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-Time Texturing for 6D Object Instance Detection from RGB Images

Rojtberg

Kuijper

2019

2019 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)

View full text Add to dashboard Cite

For objected detection, the availability of color cues strongly influences detection rates and is even a prerequisite for many methods. However, when training on synthetic CAD data, this information is not available. We therefore present a method for generating a texture-map from image sequences in real-time. The method relies on 6 degree-of-freedom poses and a 3D-model being available. In contrast to previous works this allows interleaving detection and texturing for upgrading the detector on-the-fly. Our evaluation shows that the acquired texture-map significantly improves detection rates using the LINEMOD [5] detector on RGB images only. Additionally, we use the texture-map to differentiate instances of the same object by surface color.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Using Noisy Pose Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Texturing for 6D Object Instance Detection from RGB Images

Rojtberg

Kuijper

2019

2019 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)

View full text Add to dashboard Cite

show abstract

“…[163], [167], [168], [159], [160] use both real and synthetic images to train. The 2D-driven 3D methods and the 3D BB detectors work at the level of categories, and the 6D methods [40], [38], [30], [31], [32], [4], [35] work at instance-level. Figure 3 depicts the overall schematic representation of the classification & regression-based methods.…”

Section: B Regressionmentioning

confidence: 99%

A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators

Şahin

Garcia-Hernando

Sock

et al. 2020

Image and Vision Computing

View full text Add to dashboard Cite

Object pose recovery has gained increasing attention in the computer vision field as it has become an important problem in rapidly evolving technological areas related to autonomous driving, robotics, and augmented reality. Existing review-related studies have addressed the problem at visual level in 2D, going through the methods which produce 2D bounding boxes of objects of interest in RGB images. The 2D search space is enlarged either using the geometry information available in the 3D space along with RGB (Mono/Stereo) images, or utilizing depth data from LIDAR sensors and/or RGB-D cameras. 3D bounding box detectors, producing category-level amodal 3D bounding boxes, are evaluated on gravity aligned images, while full 6D object pose estimators are mostly tested at instance-level on the images where the alignment constraint is removed. Recently, 6D object pose estimation is tackled at the level of categories. In this paper, we present the first comprehensive and most recent review of the methods on object pose recovery, from 3D bounding box detectors to full 6D pose estimators. The methods mathematically model the problem as a classification, regression, classification & regression, template matching, and point-pair feature matching task. Based on this, a mathematical-model-based categorization of the methods is established. Datasets used for evaluating the methods are investigated with respect to the challenges, and evaluation metrics are studied. Quantitative results of experiments in the literature are analysed to show which category of methods best performs across what types of challenges. The analyses are further extended comparing two methods, which are our own implementations, so that the outcomes from the public results are further solidified. Current position of the field is summarized regarding object pose recovery, and possible research directions are identified.

show abstract

A Knowledge Transfer Method for Unsupervised Pose Keypoint Detection Based on Domain Adaptation and CAD Models

Kong

Delong

2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Vision‐based pose estimation is a basic task in many industrial fields such as bin‐picking, autonomous assembly, and augmented reality. One of the most commonly used pose estimation methods first detects the 2D pose keypoints in the input image and then calculates the 6D pose using a pose solver. Recently, deep learning is widely used in pose keypoint detection and performs excellent accuracy and adaptability. However, its over‐reliance on sufficient and high‐quality samples and supervision is prominent, particularly in the industrial field, leading to high data cost. Based on domain adaptation and computer‐aided‐design (CAD) models, herein, a virtual‐to‐real knowledge transfer method for pose keypoint detection to reduce the data cost of deep learning is proposed. To address the disorder of knowledge flow, a viewpoint‐driven feature alignment strategy is proposed to simultaneously eliminate interdomain differences and preserve intradomain differences. The shape invariance of rigid objects is then introduced as constraints to address the large assumption space problem in the regressive domain adaptation. The multidimensional experimental results demonstrate the superiority of the method. Without real annotations, the normalized pixel error of keypoint detection is reported as 0.033, and the proportion of pixel errors lower than 0.05 is up to 92.77%.

show abstract

Real-Time Seamless Single Shot 6D Object Pose Prediction

Cited by 715 publications

References 40 publications

Real-Time Texturing for 6D Object Instance Detection from RGB Images

Real-Time Texturing for 6D Object Instance Detection from RGB Images

A review on object pose recovery: From 3D bounding box detectors to full 6D pose estimators

A Knowledge Transfer Method for Unsupervised Pose Keypoint Detection Based on Domain Adaptation and CAD Models

Contact Info

Product

Resources

About