Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

You, Yang; Ye, Zelin; Lou, Yujing; Li, Chengkun; Li, Yong-Lu; Ma, Lizhuang; Wang, Weiming; Lu, Cewu

doi:10.1109/cvpr52688.2022.00126

Cited by 11 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. First, the tooth model needs to be preprocessed to segment individual teeth and establish their respective OBB (You et al 2022). Then, the ideal dental arch curve is fitted by the Beta curve and the Spee curve to determine the target pose for orthodontic treatment.…”

Section: The Proposed Opp-igwo Methodsmentioning

confidence: 99%

“…Due to the rigid body properties of teeth, two teeth cannot interfere with each other or even penetrate each other in the same space and time. Therefore, we establish an oriented bounding box (OBB) (You et al 2022) for the segmented teeth respectively and use the separation axis theorem (Liang et al 2015) to quickly judge the collision between teeth. For any group of OBB in three-dimensional space, there are 15 potential separation axes, of which 6 are the three-axis directions of bounding boxes A and B respectively and the remaining 9 are the cross-product directions of any two coordinate axis vectors in bounding boxes A and B.…”

Section: The Proposed Opp-igwo Methodsmentioning

confidence: 99%

See 1 more Smart Citation

An Orthodontic Path Planning Method Based on Improved Gray Wolf Optimization Algorithm

Chen

2023

Preprint

View full text Add to dashboard Cite

Automatic tooth arrangement and path planning plays an essential role in computer-aided orthodontic treatment. However, state-of-the-art methods have some shortcomings: low efficiency, excessive cost of displacements or collisions and insufficient accuracy. To address these issues, this paper proposes an innovative orthodontic path planning method based on the improved gray wolf optimization algorithm, which is called OPP-IGWO. First, the tooth model is preprocessed to obtain initial pose in which each tooth is segmented and built up with an oriented bounding box (OBB). Next, the target pose of each tooth is determined through the ideal dental arch curve and the optimal jaw principle. Finally, the path from the initial pose to the target pose of each tooth is planned based on IGWO, which is improved mainly from three aspects: (1) The greedy idea is adopted to initialize the gray wolf population based on dental interpolation. (2) The linear convergence factor in the traditional gray wolf optimization algorithm (GWO) is replaced with a non-linear convergence factor. (3) We propose a position update strategy based on a dynamic weighting approach, which introduces a learning rate for each gray wolf. The experimental results show that our OPP-IGWO method outperforms the state-of-the-art methods. Compared with improved genetic algorithm (IGA), normal simplified mean particle swarm optimization algorithm (NSMPSO), multiparticle improved swarm optimization (Mutil-IPSO) and improved artificial bee colony algorithm (IABC), the OPP-IGWO has an improvement on performance by 14.22%, 11.46%, 6.32% and 5.27% respectively.

show abstract

Section: The Proposed Opp-igwo Methodsmentioning

confidence: 99%

Section: The Proposed Opp-igwo Methodsmentioning

confidence: 99%

An Orthodontic Path Planning Method Based on Improved Gray Wolf Optimization Algorithm

Chen

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…It is commonly not easy to extend such methods for 3D keypoint estimation of general shapes which usually present diverse geometric topologies and irregular numbers of keypoints. Recently, You et al [YLL*20b] proposed the first large‐scale 3D keypoint dataset of 16 general object categories in ShapeNet [CFG*15] and established a benchmark for the task of keypoint prediction. All the methods evaluated in [YLL*20b] focus on complete point cloud input, where the key‐point prediction can be converted into a classification task for each point.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, You et al [YLL*20b] proposed the first large‐scale 3D keypoint dataset of 16 general object categories in ShapeNet [CFG*15] and established a benchmark for the task of keypoint prediction. All the methods evaluated in [YLL*20b] focus on complete point cloud input, where the key‐point prediction can be converted into a classification task for each point. However, explicit or complete geometry is typically expensive to obtain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

3D Keypoint Estimation Using Implicit Representation Learning

Zhu

Du²,

Huang

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

In this paper, we tackle the challenging problem of 3D keypoint estimation of general objects using a novel implicit representation. Previous works have demonstrated promising results for keypoint prediction through direct coordinate regression or heatmap‐based inference. However, these methods are commonly studied for specific subjects, such as human bodies and faces, which possess fixed keypoint structures. They also suffer in several practical scenarios where explicit or complete geometry is not given, including images and partial point clouds. Inspired by the recent success of advanced implicit representation in reconstruction tasks, we explore the idea of using an implicit field to represent keypoints. Specifically, our key idea is employing spheres to represent 3D keypoints, thereby enabling the learnability of the corresponding signed distance field. Explicit key‐points can be extracted subsequently by our algorithm based on the Hough transform. Quantitative and qualitative evaluations also show the superiority of our representation in terms of prediction accuracy.

show abstract

ReAGFormer: Reaggregation Transformer with Affine Group Features for 3D Object Detection

Kang

Liu

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

Cited by 11 publications

References 24 publications

An Orthodontic Path Planning Method Based on Improved Gray Wolf Optimization Algorithm

An Orthodontic Path Planning Method Based on Improved Gray Wolf Optimization Algorithm

3D Keypoint Estimation Using Implicit Representation Learning

ReAGFormer: Reaggregation Transformer with Affine Group Features for 3D Object Detection

Contact Info

Product

Resources

About