Latent-Class Hough Forests for 3D Object Detection and Pose Estimation

By Alykhan Tejani, Danhang Tang, Rigas Kouskouridas, Tae-Kyun Kim. 2014

320 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 ap-ba proaches to 3D pose estimation [3,4,39,44,46] assume that the true 3D shape of the object instance is known.”
T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects (2017, background): “[47] presented a dataset with 2 texture-less and 4 textured objects.”
Learning descriptors for object recognition and 3D pose estimation (2015, background): “The very recent [4, 34] do not use templates but rely on recognition of local patches in stead.”
H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions (2019, background): “A significant amount of research has focused on visual understanding of humans [8, 25, 36, 40, 59, 65, 70, 74] and objects [4, 28, 64, 66], in isolation from each other.”
Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd (2015, methodology): “However, compared to our work, this method is based on holistic images of the objects, which is prone to occlusions [31] and only evaluated on a public dataset that contains no foreground occlusions.”
Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review (2020, methodology): “[Tejani et al., 2014] trained a Hough forest for 6D pose estimation from an RGB-D image.”
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.”
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].”
BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth (2017, methodology): “To tackle clutter and partial occlusions, [1] and [21] rely on local patches recognition performed with Random Forests.”
Global Hypothesis Generation for 6D Object Pose Estimation (2016, methodology): “[27] proposed an iterative latent-class Hough-voting-scheme for object classiﬁcation and 3D pose estimation with RGB-D data as input.”
The ACRV picking benchmark: A robotic shelf picking benchmark to foster reproducible research (2016, unknown): “[14] introduced a 2D/3D database for multipleinstance detection with considerable clutter and foreground occlusion.”
BOP Challenge 2020 on 6D Object Localization (2020, unknown): “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 – 50000 54 721 721 3041 3041 HB [30] ∗ 33 – 50000 4420 13000 300 67542 1630 YCB-V [53] ∗ 21 113198 50000 – 20738 900 98547 4123 RU-APC [45] 14 – – ”
Completing 3D object shape from one depth image (2015, background): “[35] propose a tree based structured prediction for determining object and pose from RGB-D”
Deep Template-based Object Instance Detection (2021, background): “Despite this, efforts have been made to capture such real datasets [3, 13, 16, 33, 7, 34] and to combine them together [17].”
BOP: Benchmark for 6D Object Pose Estimation (2018, methodology): “LM/LM-O [14,1] IC-MI [34] IC-BIN [7] T-LESS [16] RU-APC [28] TUD-L - new TYO-L - new”