Single image 3D object detection and pose estimation for grasping

By Menglong Zhu, Konstantinos G. Derpanis, Yinfei Yang, Samarth Brahmbhatt, Mabel M. Zhang, Cody J. Phillips, Matthieu Lecce, Kostas Daniilidis. 2014

251 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

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

Citations in the corpus

Transporter Networks: Rearranging the Visual World for Robotic Manipulation (2020, background): “Considerable research in vision for manipulation has been devoted to object detectors and pose estimators [17, 18, 19, 20, 21].”
CLIPort: What and Where Pathways for Robotic Manipulation (2021, background): “Traditionally, perception for manipulation has centered around object detectors, segmentors, and pose estimators [21, 22, 23, 24, 25, 26].”
3D Bounding Box Estimation Using Deep Learning and Geometry (2016, methodology): “A similar method for estimating the pose using the projection of CAD model object instances has been explored by [29] in a robotics table-top setting where the detection problem is less challenging.”
Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation (2022, methodology): “Traditionally, methods in robot perception have used explicit “object” representations like instance segmentations, object classes, poses [18, 19, 20, 21, 22, 23].”
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (2019, methodology): “Classical methods rely on detecting and matching keypoints with known object models [1, 7, 9, 27, 44].”
PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation (2017, unknown): “These include keypoint matching between 2D images and their corresponding 3D CAD models [1, 5, 37], or aligning 3D-reconstructed models with ground-truth models to recover the object poses [28, 9].”
Sliding Shapes for 3D Object Detection in Depth Images (2014, background): “5D Detector: There are several seminal works that try to extend standard 2D imagebased object detector to use depth maps [24, 80, 81, 25, 82].”
GDRNPP: A Geometry-Guided and Fully Learning-Based Object Pose Estimator (2021, unknown): “It has wide applicability to many real-world tasks such as robotic manipulation [1], [2], [3], augmented reality [4], [5] and autonomous driving [6], [7].”
Real-Time Seamless Single Shot 6D Object Pose Prediction (2017, methodology): “RGB-D methods were used on indoor robots for 3D object recognition, pose estimation, grasping and manipulation [3, 4, 5, 13, 14, 40].”
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud (2018, methodology): “[1, 44, 23] exploited the similarity between 3D objects and the CAD models.”
PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (2018, methodology): “Traditional methods mainly rely on template matching techniques [16, 12, 14, 42], which are sensitive to cluttered environments and appearance changes.”
Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation (2021, background): “For known objects, one may rely on pose estimation [36, 46, 49], however, this does not enable”
PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (2019, background): “It is an important component in many real-world applications, such as robotic grasping and manipulation [6, 48, 55], autonomous driving [11, 5, 53], augmented reality [31] and so on.”
Structured Prediction of Unobserved Voxels from a Single Depth Image (2016, unknown): “to aid robot grasping [56, 62] or navigation.”
6-DoF object pose from semantic keypoints (2017, methodology): “To address class variability and viewpoint, various approaches have used a collection of 2D appearance-based part templates trained separately on discretized views [1], [13], [14], [15], [16].”
From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network (2019, unknown): “[36], [37], [38], [39] exploited the similarity between 3D objects and the CAD models.”
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image (2016, background): “[33], with the goal to grasp objects which requires medium accuracy.”