3D Pose Regression Using Convolutional Neural Networks

Mahendran, Siddharth; Ali, Haider; Vidal, René

doi:10.1109/cvprw.2017.73

Cited by 78 publications

(86 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid this problem, the newer PoseCNN architecture [38] is trained to predict 6D object pose from a single RGB image in multiple stages, by decoupling the translation and rotation predictors. A geodesic loss function more suitable for optimizing over 3D rotations have been suggested in [23]. Another way to address this issue has recently emerged.…”

Section: Related Workmentioning

confidence: 99%

Real-Time Seamless Single Shot 6D Object Pose Prediction

Tekin

Sinha

Fua

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

709

546

View full text Add to dashboard Cite

We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses. Unlike a recently proposed single-shot technique for this task [11] that only predicts an approximate 6D pose that must then be refined, ours is accurate enough not to require additional post-processing. As a result, it is much faster -50 fps on a Titan X (Pascal) GPU -and more suitable for real-time processing. The key component of our method is a new CNN architecture inspired by [28,29] that directly predicts the 2D image locations of the projected vertices of the object's 3D bounding box. The object's 6D pose is then estimated using a PnP algorithm.For single object and multiple object pose estimation on the LINEMOD and OCCLUSION datasets, our approach substantially outperforms other recent CNN-based approaches [11,26] when they are all used without postprocessing. During post-processing, a pose refinement step can be used to boost the accuracy of these two methods, but at 10 fps or less, they are much slower than our method.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-Time Seamless Single Shot 6D Object Pose Prediction

Tekin

Sinha

Fua

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

709

546

View full text Add to dashboard Cite

show abstract

“…Compared to most previous works [33,25,17], our method does not require the intermediate prediction of 2D/3D key points. In addition, we assume a full perspective model, which is a more challenging setting than previous works of estimating discrete/continuous viewpoint angles (azimuth) [4] or recovering the rotation matrices only [14]. Our expected goal is that by projecting the fine-grained 3D model according to the regressed pose estimation, the projection can align well with the object in the 2D image.…”

Section: Fine-grained 2d Imagementioning

confidence: 99%

3D Pose Estimation for Fine-Grained Object Categories

Wang

Tan

Yang

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Existing object pose estimation datasets are related to generic object types and there is so far no dataset for fine-grained object categories. In this work, we introduce a new large dataset to benchmark pose estimation for fine-grained objects, thanks to the availability of both 2D and 3D fine-grained data recently. Specifically, we augment two popular fine-grained recognition datasets (StanfordCars and CompCars) by finding a fine-grained 3D CAD model for each sub-category and manually annotating each object in images with 3D pose. We show that, with enough training data, a full perspective model with continuous parameters can be estimated using 2D appearance information alone. We achieve this via a framework based on Faster/Mask R-CNN. This goes beyond previous works on category-level pose estimation, which only estimate discrete/continuous viewpoint angles or recover rotation matrices often with the help of key points. Furthermore, with fine-grained 3D models available, we incorporate a dense 3D representation named as location field into the CNN-based pose estimation framework to further improve the performance. The new dataset is available at

show abstract

“…The number of discretization bins is chosen as b = 500 in our experiments. An alternative would be to directly regress each scalar using methods similar to [15,27], but we did not pursue that here.…”

Section: Implementation Detailsmentioning

confidence: 99%

A Geometric Approach to Obtain a Bird's Eye View From an Image

Abbas

Zisserman

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

The objective of this paper is to rectify any monocular image by computing a homography matrix that transforms it to a bird's eye (overhead) view.We make the following contributions: (i) we show that the homography matrix can be parameterised with only four parameters that specify the horizon line and the vertical vanishing point, or only two if the field of view or focal length is known; (ii) We introduce a novel representation for the geometry of a line or point (which can be at infinity) that is suitable for regression with a convolutional neural network (CNN); (iii) We introduce a large synthetic image dataset with ground truth for the orthogonal vanishing points, that can be used for training a CNN to predict these geometric entities; and finally (iv) We achieve state-of-theart results on horizon detection, with 74.52% AUC on the Horizon Lines in the Wild dataset. Our method is fast and robust, and can be used to remove perspective distortion from videos in real time.

show abstract

3D Pose Regression Using Convolutional Neural Networks

Cited by 78 publications

References 12 publications

Real-Time Seamless Single Shot 6D Object Pose Prediction

Real-Time Seamless Single Shot 6D Object Pose Prediction

3D Pose Estimation for Fine-Grained Object Categories

A Geometric Approach to Obtain a Bird's Eye View From an Image

Contact Info

Product

Resources

About