Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach

By Reyes Rios-Cabrera, Tinne Tuytelaars. 2013

168 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.”
FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation (2021, unknown): “Traditional methods utilize hand-coded [19, 20, 51] templates or features optimized by surrogate objectives [2, 61, 67, 28] from RGBD data and perform correspondence grouping and hypothesis verification.”
6-DoF object pose from semantic keypoints (2017, background): “In recent years, template-based methods have received renewed interest due to the advent of accelerated matching schemes and their ability to detect textureless objects by way of focusing their model description on the object shape [9], [10], [11], [7], [12].”
Learning 6D Object Pose Estimation Using 3D Object Coordinates (2014, methodology): “We also compare to [21] who optimize the Hinterstoisser templates in a discriminative fashion to boost performance and speed.”
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (2019, methodology): “Classical approaches first extract features from RGB-D data and perform correspondence grouping and hypothesis verification [3, 12, 13, 15, 26, 33, 38].”
Latent-Class Hough Forests for 3D Object Detection and Pose Estimation (2014, background): “Therefore, similarly to [28], we argue a more meaningful evaluation is to sort all detection scores across all images and calculate the general performance of the detector, given by the precision-recall curves.”
T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects (2017, background): “Further to the above, there exist RGB datasets such as [13, 50, 38, 25], for which the ground truth is provided only in the form of 2D bounding boxes.”
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image (2016, methodology): “However, pose estimation from RGB images was not presented in [7] nor [22].”
Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd (2015, methodology): “Most representative are techniques based on template matching, like LINEMOD [14], its extension [25] and the Distance Transform approaches [21].”
DPOD: 6D Pose Object Detector and Refiner (2019, background): “Template matching approaches, e.g. [11, 12, 29], render synthetic image patches from different viewpoints distributed on a sphere around the 3D model of the object and store them as a database of templates.”
Real-Time Seamless Single Shot 6D Object Pose Prediction (2017, background): “[30] extended their work using discriminative learning and cascaded detections for higher accuracy and efficiency respectively.”