3D Medical Objects Retrieval Approach Using SPHARMs Descriptor and Network Flow as Similarity Measure

Bergamasco, Leila C. C.; Lima, Karla Roberta; Rochitte, Carlos Eduardo; Nunes, Fátima L. S.

doi:10.1109/sibgrapi.2018.00049

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3D object retrieval is an important topic in computer vision and has received a surge of research attention owing to its close relationship with various geometry related applications, e.g., VR/AR [20,26,48], medical imaging [25,6,56] and 3D printing [49]. With the development of 3D model acquisition technology, large amounts of 3D models are available for free, e.g., the large-scale repository ShapeNet [8].…”

Section: Introductionmentioning

confidence: 99%

View N-Gram Network for 3D Object Retrieval

Huang

Bai

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

How to aggregate multi-view representations of a 3D object into an informative and discriminative one remains a key challenge for multi-view 3D object retrieval. Existing methods either use view-wise pooling strategies which neglect the spatial information across different views or employ recurrent neural networks which may face the efficiency problem. To address these issues, we propose an effective and efficient framework called View N-gram Network (VNN). Inspired by n-gram models in natural language processing, VNN divides the view sequence into a set of visual n-grams, which involve overlapping consecutive view sub-sequences. By doing so, spatial information across multiple views is captured, which helps to learn a discriminative global embedding for each 3D object. Experiments on 3D shape retrieval benchmarks, including ModelNet10, ModelNet40 and ShapeNetCore55 datasets, demonstrate the superiority of our proposed method. * indicates equal contributions.

show abstract