Deep Hough Voting for Robust Global Registration

Lee, Jun-Ha; Kim, Seungwook; Cho, Minsu; Park, Jaesik

doi:10.1109/iccv48922.2021.01569

Cited by 79 publications

(14 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We further compare with recent deep robust estimators: 3DRegNet [22], DGR [7], PointDSC [3], DHVR [18] and PCAM [6] on 3DMatch and KITTI. Following common practice, we report RTE, RRE and RR on both benchmarks.…”

Section: D2 Comparison With Deep Robust Estimatorsmentioning

confidence: 99%

Geometric Transformer for Fast and Robust Point Cloud Registration

Zheng¹,

Yu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods bypass the detection of repeatable keypoints which is difficult in low-overlap scenarios, showing great potential in registration. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it robust in low-overlap cases and invariant to rigid transformation. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Our method improves the inlier ratio by 17%∼30% and the registration recall by over 7% on the challenging 3DLoMatch benchmark. The code and models will be released at https://github. com/qinzheng93/GeoTransformer.

show abstract

Section: D2 Comparison With Deep Robust Estimatorsmentioning

confidence: 99%

Geometric Transformer for Fast and Robust Point Cloud Registration

Zheng¹,

Yu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Beyond the former types of methods that require the network to implicitly remember the target objects during train-ing, registration based methods [2,15,16,33,46,55,59] treat this task as point cloud registration and could estimate the 6D pose between two novel inputs. However, they usually consider the registration between two similar-sized targets.…”

Section: Object 6d Pose Estimation Algorithmsmentioning

confidence: 99%

Unseen Object 6D Pose Estimation: A Benchmark and Baselines

Gou¹,

Pan²,

Fang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Estimating the 6D pose for unseen objects is in great demand for many real-world applications. However, current state-of-the-art pose estimation methods can only handle objects that are previously trained. In this paper, we propose a new task that enables and facilitates algorithms to estimate the 6D pose estimation of novel objects during testing. We collect a dataset with both real and synthetic images and up to 48 unseen objects in the test set. In the mean while, we propose a new metric named Infimum ADD (IADD) which is an invariant measurement for objects with different types of pose ambiguity. A two-stage baseline solution for this task is also provided. By training an endto-end 3D correspondences network, our method finds corresponding points between an unseen object and a partial view RGBD image accurately and efficiently. It then calculates the 6D pose from the correspondences using an algorithm robust to object symmetry. Extensive experiments show that our method outperforms several intuitive baselines and thus verify its effectiveness. All the data, code and models will be made publicly available. Project page: www.graspnet.net/unseen6d

show abstract

“…RGM [FLLW21] introduces a deep graph matching‐based framework for registration, which takes both local geometry and graph topological structure into consideration. By contrast, some other methods such as [CDK20, PRG*20, BLZ*21, LKCP21, CSYT22] focus more on the removal of outlier correspondences. For example, DGR [CDK20] and 3DRegNet [PRG*20] utilize a classifier to predict a confidence value for each correspondence.…”

Section: Related Workmentioning

confidence: 99%

UTOPIC: Uncertainty‐aware Overlap Prediction Network for Partial Point Cloud Registration

Chen

Gong

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

High‐confidence overlap prediction and accurate correspondences are critical for cutting‐edge models to align paired point clouds in a partial‐to‐partial manner. However, there inherently exists uncertainty between the overlapping and non‐overlapping regions, which has always been neglected and significantly affects the registration performance. Beyond the current wisdom, we propose a novel uncertainty‐aware overlap prediction network, dubbed UTOPIC, to tackle the ambiguous overlap prediction problem; to our knowledge, this is the first to explicitly introduce overlap uncertainty to point cloud registration. Moreover, we induce the feature extractor to implicitly perceive the shape knowledge through a completion decoder, and present a geometric relation embedding for Transformer to obtain transformation‐invariant geometry‐aware feature representations. With the merits of more reliable overlap scores and more precise dense correspondences, UTOPIC can achieve stable and accurate registration results, even for the inputs with limited overlapping areas. Extensive quantitative and qualitative experiments on synthetic and real benchmarks demonstrate the superiority of our approach over state‐of‐the‐art methods.

show abstract

Deep Hough Voting for Robust Global Registration

Cited by 79 publications

References 44 publications

Geometric Transformer for Fast and Robust Point Cloud Registration

Geometric Transformer for Fast and Robust Point Cloud Registration

Unseen Object 6D Pose Estimation: A Benchmark and Baselines

UTOPIC: Uncertainty‐aware Overlap Prediction Network for Partial Point Cloud Registration

Contact Info

Product

Resources

About