BOP Challenge 2020 on 6D Object Localization

@inproceedings{Hodan2020BOPC2,
  title={BOP Challenge 2020 on 6D Object Localization},
  author={Tom{\'a}s Hodan and Martin Sundermeyer and Bertram Drost and Yann Labb{\'e} and Eric Brachmann and Frank Michel and Carsten Rother and Jiri Matas},
  booktitle={ECCV Workshops},
  year={2020}
}
This paper presents the evaluation methodology, datasets, and results of the BOP Challenge 2020, the third in a series of public competitions organized with the goal to capture the status quo in the field of 6D object pose estimation from an RGB-D image. In 2020, to reduce the domain gap between synthetic training and real test RGB images, the participants were provided 350K photorealistic training images generated by BlenderProc4BOP, a new open-source and light-weight physically-based renderer… Expand

Figures and Tables from this paper

T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression
TLDR
This work proposes T6D-Direct, a real-time single-stage direct method with a transformer-based architecture built on DETR to perform 6D multi-object pose direct estimation that achieves the fastest inference time, and the pose estimation accuracy is comparable to state-of-the-art methods. Expand
A Survey on Deep Learning Based Methods and Datasets for Monocular 3D Object Detection
TLDR
This study investigates the major breakthroughs and current progress in deep learning-based monocular 3D object detection, and presents the key concepts and detailed descriptions of representative single-stage and multiple-stage detection solutions. Expand
CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds
TLDR
This work presents an augmented autoencoder (AAE) for learning a latent code that encodes 6D object pose information for pose regression, and a lightweight data synthesis pipeline that creates synthetic point cloud segments for training. Expand
6D Object Pose Estimation using Keypoints and Part Affinity Fields
TLDR
This work presents a two-step pipeline for estimating the 6DoF translation and orientation of known objects and finds that using PAFs to assemble detected keypoints into object instances proves advantageous over only using heatmaps. Expand
Supplementary Material of GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation
In this supplementary material, we provide i) details of PnP/RANSAC, ii) detailed evaluation results on YCBV [17], iii) results on LM-O [1] and YCB-V [17] under BOP [5] setup, and iv) qualitativeExpand
PyraPose: Feature Pyramids for Fast and Accurate Object Pose Estimation under Domain Shift
TLDR
It is argued that patch-based approaches, instead of encoder-decoder networks, are more suited for synthetic-to-real transfer because local to global object information is better represented. Expand
Data-Driven Object Pose Estimation in a Practical Bin-Picking Application
TLDR
This paper addresses the problem of pose estimation from 2D images for textureless industrial metallic parts for a semistructured bin-picking task with a data-driven approach based on convolutional neural networks (CNN), without the need for a hard-coded geometry of the manipulated object. Expand
Optimizing RGB-D Fusion for Accurate 6DoF Pose Estimation
TLDR
A new pose estimation system which ensures highest both 2D and 3D precision and a novel refinement method which ensures optimal precision as both RGB and depth information are fused is proposed. Expand
SynPick: A Dataset for Dynamic Bin Picking Scene Understanding
TLDR
This work presents SynPick, a synthetic dataset for dynamic scene understanding in bin-picking scenarios, and demonstrates the usefulness of tracking poses during manipulation instead of single-shot estimation even with a naive filtering approach. Expand
Bridging the Performance Gap Between Pose Estimation Networks Trained on Real And Synthetic Data Using Domain Randomization
TLDR
A new method is introduced, which bridges the gap between real and synthetically trained networks and utilizes 3D point clouds, which allows both for domain randomization in 3D and to use neighboring geometric information during inference. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 56 REFERENCES
BOP: Benchmark for 6D Object Pose Estimation
TLDR
A benchmark for 6D pose estimation of a rigid object from a single RGB-D input image shows that methods based on point-pair features currently perform best, outperforming template matching methods, learning-based methods and methodsbased on 3D local features. Expand
DPOD: 6D Pose Object Detector and Refiner
TLDR
A novel deep learning method that estimates dense multi-class 2D-3D correspondence maps between an input image and available 3D models and demonstrates that a large number of correspondences is beneficial for obtaining high-quality 6D poses both before and after refinement. Expand
HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects
TLDR
This paper presents a dataset for 6D pose estimation that covers training from 3D models (both textured and textureless), scalability, occlusions, and changes in light conditions and object appearance, and presents a set of benchmarks to test various desired detector properties. Expand
A Hybrid Approach for 6DoF Pose Estimation
We propose a method for 6DoF pose estimation of rigid objects that uses a state-of-the-art deep learning based instance detector to segment object instances in an RGB image, followed by a point-pairExpand
Augmented Autoencoders: Implicit 3D Orientation Learning for 6D Object Detection
TLDR
This novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain Randomization and achieves state-of-the-art performance on the T-LESS dataset both in the RGB and RGB-D domain. Expand
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again
TLDR
A novel method for detecting 3D model instances and estimating their 6D poses from RGB data in a single shot that competes or surpasses current state-of-the-art methods that leverage RGBD data on multiple challenging datasets. Expand
EPOS: Estimating 6D Pose of Objects With Symmetries
TLDR
A new method for estimating the 6D pose of rigid objects with available 3D models from a single RGB input image using a robust and efficient variant of the PnP-RANSAC algorithm, which outperforms all RGB and most RGB-D and D methods on the T-LESS and LM-O datasets. Expand
Introducing MVTec ITODD — A Dataset for 3D Object Recognition in Industry
We introduce the MVTec Industrial 3D Object Detection Dataset (MVTec ITODD), a public dataset for 3D object detection and pose estimation with a strong focus on objects, settings, and requirementsExpand
Learning 6D Object Pose Estimation Using 3D Object Coordinates
TLDR
This work addresses the problem of estimating the 6D Pose of specific objects from a single RGB-D image by presenting a learned, intermediate representation in form of a dense 3D object coordinate labelling paired with a dense class labelling. Expand
BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth
  • Mahdi Rad, V. Lepetit
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
TLDR
A novel method for 3D object detection and pose estimation from color images only that uses segmentation to detect the objects of interest in 2D even in presence of partial occlusions and cluttered background and is the first to report results on the Occlusion dataset using color imagesonly. Expand
...
1
2
3
4
5
...