Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image

By Eric Brachmann, Frank Michel, Alexander Krull, Michael Ying Yang, Stefan Gumhold, Carsten Rother. 2016

546 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

OctNet: Learning Deep 3D Representations at High Resolutions (2016, background): “Most existing approaches to 3D pose estimation [3,4,38,43,45] assume that the true 3D shape of the object instance is known.”
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes (2017, methodology): “Using the semantic labeling results and 3D object coordinate regression results, the 6D pose is recovered using the pre-emptive RANSAC as in [11] on RGB-D data.”
Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation (2019, methodology): “The performance is also better than the best learning-based methods [2, 15] in the benchmark [10].”
Implicit 3D Orientation Learning for 6D Object Detection from RGB Images (2018, background): “[35,40,4,28] In consequence, some works [17,40] have proposed to train on synthetic images rendered from a 3D model, yielding a great data source with pose labels free of charge.”
CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation (2019, methodology): “We split it into training and test sets according to [3].”
HybridPose: 6D Object Pose Estimation Under Hybrid Representations (2020, background): “Besides keypoints, another common intermediate representation is the coordinate of every image pixel in the 3D physical world, which provides dense 2D-3D correspondences for pose alignment, and is robust under occlusion [3, 4, 30, 20].”
InLoc: Indoor Visual Localization with Dense Matching and View Synthesis (2019, background): “In contrast, indoor localization [11], [12], [45], [69], [71], [76], [85], [90] has received less attention in the last years.”
Visual Camera Re-Localization From RGB and RGB-D Images Using DSAC (2020, methodology): “In this work, and our previous work [5], [14], [15], [16], [17], we choose a fixed M and train the system to adapt to this particular setting.”
Understanding the Limitations of CNN-Based Absolute Camera Pose Regression (2019, methodology): “These matches are established by descriptor matching [21, 37, 39, 59, 63, 68, 69, 81] or by regressing 3D coordinates from pixel patches [8–10, 16, 23, 43, 46, 47, 65].”
iNeRF: Inverting Neural Radiance Fields for Pose Estimation (2020, unknown): ““With Real Pose Labels” refers to methods that additionally train on 15% of the test data following [2] and therefore have seen real posed images, rather than only synthetic posed images.”
Policy transfer via modularity (2017, methodology): “detector, using one of various image algorithms for such tasks [30], [31], [32], [33].”
PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (2018, methodology): “We evaluate our method using two standard metrics: 2D projection metric [3] and average 3D distance of model points (ADD) metric [15].”
6-DoF object pose from semantic keypoints (2017, background): “s that they are inadequate for addressing textureless objects and their performance is susceptible to scene clutter. An alternative to sparse discriminative keypoints is offered by dense methods [9], [10], [11], [12], where every pixel or patch is voting for the object pose. These approaches are als”
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions (2018, background): “They learn features with stable appearance over time [17, 47, 49], train classifiers for place recognition [12, 28, 37, 76], and train CNNs to regress 2D-3D matches [8, 9, 60] or camera poses [19, 31, 74].”
Segmentation-Driven 6D Object Pose Estimation (2018, methodology): “We report the commonly-used 2D reprojection (REP) error [3].”
Image-Based Localization Using LSTMs for Structured Feature Correlation (2016, methodology): “One drawback of the PoseNet approach is its relative inaccuracy [5].”
BOP: Benchmark for 6D Object Pose Estimation (2018, background): “[34,24,18,2,36,21,27,25], but it is unclear which methods perform well and in which scenarios.”
Real-Time Seamless Single Shot 6D Object Pose Prediction (2017, methodology): “whose pose can only be computed up to one degree of rotational freedom, we modify slightly the metric as in [2, 8] and compute”