Learning 6D Object Pose Estimation Using 3D Object Coordinates

By Eric Brachmann, Alexander Krull, Frank Michel, Stefan Gumhold, Jamie Shotton, Carsten Rother. 2014

868 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, 3D Vision & Pose

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

In Control and Systems Engineering

In 3D Vision & Pose

Citations in the corpus

Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “VQ upgrades object instance recog-pre-condition nition [23, 85, 126, 155] to deal with video (frequent FoV changes, objects entering/exiting the view) and to reason about objects in the context of a 3D environment.”
RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, background): “, TUM Textureless, Object Segmentation, Object Discovery and PTB, can be found in [7, 61, 73] and [29], respectively.”
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.”
OctNetFusion: Learning Depth Fusion from Data (2017, methodology): “Shape Completion: If exact 3D models are available, missing surfaces can be completed by detecting the objects and fitting 3D models to the observations [3, 21].”
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes (2017, methodology): “From the table, we can also see that methods which use 3D coordinate regression [25], [2], [7] perform poorly on the Eggbox due to symmetry, while our method is able to handle it well.”
3D-FUTURE: 3D Furniture Shape with TextURE (2020, methodology): “Recentworks thus employ RGB-D sensors and deep learning to improve keypoints detection or directly predict 6DoF pose from images (Kehl et al. 2016; Brachmann et al. 2014; Bo et al. 2014; Hinterstoisser et al. 2012; Xiang et al. 2017; Peng et al. 2019; Song et al. 2020; Tekin et al. 2018; Rad and Lep”
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again (2017, background): “Features can either be an encoding of image properties (color gradients, depth values, normal orientations) [12, 16, 18] or, more recently, the result of learning [4, 29, 5, 6, 17].”
Deep Template-based Object Instance Detection (2021, methodology): “We evaluate on the well-known Linemod [13] and Occluded Linemod [3] datasets.”
Self-supervised 6D Object Pose Estimation for Robot Manipulation (2019, background): “Recently, learning-based methods receive more attention due to their ability to generalize to different backgrounds, lighting, and occlusions [16]–[18].”
SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Control (2018, methodology): “work on object and camera pose estimation from RGB/D data using learning methods [17]–[19], most of which use some form of explicit supervision.”
Segmentation-Driven 6D Object Pose Estimation (2018, methodology): “In this paper, we focus on 6D object pose estimation from RGB images, without access to a depth map, unlike in RGBD-based methods [12, 2, 3, 28].”
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (2023, methodology): “Table 3 presents the comparison re-sults among RGBD methods on 3 core datasets from BOP: Occluded-LINEMOD [1], YCB-Video [67] and T-LESS [24].”
Policy transfer via modularity (2017, methodology): “detector, using one of various image algorithms for such tasks [30], [31], [32], [33].”
Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation (2019, methodology): “Such techniques have been successfully employed for body pose estimation [43, 17], camera relocalization [37, 46] and 6D object pose estimation [4].”
BOP Challenge 2020 on 6D Object Localization (2020, methodology): “cz/datasets. BOP Challenge 2020 on 6D Object Localization 7 Train. im. Val im. Test im. Test inst. Dataset Core Objects Real PBR Real All Used All Used LM [18] 15 { 50000 { 18273 3000 18273 3000 LM-O [3] 8 { 50000 { 1214 200 9038 1445 T-LESS [23] 30 37584 50000 { 10080 1000 67308 6423 ITODD [9] 28 {”
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image (2016, methodology): “Our method consists of three individual stages, which are conceptually similar to [2].”
Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation (2019, methodology): “(3) Experimental results on three different datasets, LineMOD [8], LineMOD Occlusion [1], and T-Less [9], showing that Pix2Pose outperforms the state-of-the-art methods even if objects are occluded or symmetric.”
Vector Neurons: A General Framework for SO(3)-Equivariant Networks (2021, background): “Most works in the literature study instance-level pose estimation, where the ground-truth canonical pose of the 3D CAD models corresponding to the input pointcloud is available [4].”
HybridPose: 6D Object Pose Estimation Under Hybrid Representations (2020, neutral): “We evaluate HybridPose on two popular benchmark datasets, Linemod [11] and Occlusion Linemod [3].”