3D Pose Regression Using Convolutional Neural Networks

Mahendran, Siddharth; Ali, Haider; Vidal, René

doi:10.1109/iccvw.2017.254

Cited by 81 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pose regression network is structured loosely on the network proposed by [16]. Their network is designed to estimate the pose of an object from a feature vector produced from a pre-trained CNN.…”

Section: Methodsmentioning

confidence: 99%

Pose Estimation from RGB Images of Highly Symmetric Objects using a Novel Multi-Pose Loss and Differential Rendering

Bengtson

Astram

Moeslund

et al. 2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

We propose a novel multi-pose loss function to train a neural network for 6D pose estimation, using synthetic data and evaluating it on real images. Our loss is inspired by the VSD (Visible Surface Discrepancy) metric and relies on a differentiable renderer and CAD models. This novel multipose approach produces multiple weighted pose estimates to avoid getting stuck in local minima. Our method resolves pose ambiguities without using predefined symmetries. It is trained only on synthetic data. We test on real-world RGB images from the T-LESS dataset, containing highly symmetric objects common in industrial settings. We show that our solution can be used to replace the codebook in a state-of-the-art approach. So far, the codebook approach has had the shortest inference time in the field. Our approach reduces inference time further while a) avoiding discretization, b) requiring a much smaller memory footprint and c) improving pose recall. 3

show abstract

Section: Methodsmentioning

confidence: 99%

Pose Estimation from RGB Images of Highly Symmetric Objects using a Novel Multi-Pose Loss and Differential Rendering

Bengtson

Astram

Moeslund

et al. 2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…The regression ConvNet methodology is also used for predicting stock prices via annual reports and text analysis (Dereli and Saraclar, 2019) and using historical data (Mehtab and Sen, 2020). Other applications include prediction of angles (Fischer et al, 2015), prediction of distances for 3D position estimates (Mahendran et al, 2017), or age estimation (Rothe et al, 2016). In the real estate field, Solovev and Pr€ ollochs (2021) choose a pretrained ConvNet to predict apartment rent prices using pictures of the floor plans as the input.…”

Section: Deep Learning For Visual Pattern Recognitionmentioning

confidence: 99%

Leveraging supplementary modalities in automated real estate valuation using comparative judgments and deep learning

Despotović

Koch

Stumpe

et al. 2023

JERER

View full text Add to dashboard Cite

PurposeIn this study the authors aim to outline new ways of information extraction for automated valuation models, which in turn would help to increase transparency in valuation procedures and thus contribute to more reliable statements about the value of real estate.Design/methodology/approachThe authors hypothesize that empirical error in the interpretation and qualitative assessment of visual content can be minimized by collating the assessments of multiple individuals and through use of repeated trials. Motivated by this problem, the authors developed an experimental approach for semi-automatic extraction of qualitative real estate metadata based on Comparative Judgments and Deep Learning. The authors evaluate the feasibility of our approach with the help of Hedonic Models.FindingsThe results show that the collated assessments of qualitative features of interior images show a notable effect on the price models and thus over potential for further research within this paradigm.Originality/valueTo the best of the authors’ knowledge, this is the first approach that combines and collates the subjective ratings of visual features and deep learning for real estate use cases.

show abstract

“…They developed a CNN regression framework for solving the 3D pose estimation problem in the continuous domain by designing a suitable representation, data augmentation and loss function that respect the non-linear structure of the 3D pose space. 9 Most of the current methods use the Euler angle or quaternion representation to train their networks. 4,9 However, Zhou et al 10 demonstrated that any representation of rotation with four or fewer dimensions is discontinuous and therefore not ideal to use in a learning task for neural networks.…”

Section: Introductionmentioning

confidence: 99%

“…9 Most of the current methods use the Euler angle or quaternion representation to train their networks. 4,9 However, Zhou et al 10 demonstrated that any representation of rotation with four or fewer dimensions is discontinuous and therefore not ideal to use in a learning task for neural networks. They proposed a 6-dimensional rotation representation (6DRep) and proved it is continuously mapped from the rotation space SO(3).…”

Section: Introductionmentioning

confidence: 99%

Automatic brain pose estimation in fetal MRI

Faghihpirayesh

Karimi

Erdoğmuş³

et al. 2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

In this paper, we present a 3D pose regression model using Convolutional Neural Networks (CNNs) for unconstrained end-to-end fetal brain pose estimation in fetal MRI. We focus on investigating across different pose representation schemes and address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data. We propose a continuous 6D rotation matrix representation for efficient and robust direct pose regression. Our model learns to predict different rotation representations of the 3D pose directly based on the MRI volume. We used a geodesic loss to evaluate our model and compare its performance with alternative methods. We trained and tested our model on arbitrarily oriented MRI volumes of fetal brains scanned in-utero at a wide gestational age range. Experimental results on synthetically transformed data, show that our method with a continuous 6D rotation matrix representation, achieved an average geodesic error of 6.33 • without any post-processing, which was smaller than the error for all competing methods. Our proposed method can be a useful base for fetal brain motion tracking, motion detection, and 3D reconstruction. Code, data, and the trained models are available at https://github.com/bchimagine/fetal-brain-pose-estimation.

show abstract

3D Pose Regression Using Convolutional Neural Networks

Cited by 81 publications

References 14 publications

Pose Estimation from RGB Images of Highly Symmetric Objects using a Novel Multi-Pose Loss and Differential Rendering

Pose Estimation from RGB Images of Highly Symmetric Objects using a Novel Multi-Pose Loss and Differential Rendering

Leveraging supplementary modalities in automated real estate valuation using comparative judgments and deep learning

Automatic brain pose estimation in fetal MRI

Contact Info

Product

Resources

About