paper-with-me

홈 › Papers

MeshCNN Fundamentals: Geometric Learning through a Reconstructable Representation

2021-05-27 · Amir Barda, Yotam Erel, Amit H. Bermano

Mesh-based learning is one of the popular approaches nowadays to learn shapes. The most established backbone in this field is MeshCNN. In this paper, we propose infusing MeshCNN with geometric reasoning to achieve higher quality learning. Through careful analysis of the way geometry is represented through-out the network, we submit that this representation should be rigid motion invariant, and should allow reconstructing the original geometry. Accordingly, we introduce the first and second fundamental forms as an edge-centric, rotation and translation invariant, reconstructable representation. In addition, we update the originally proposed pooling scheme to be more geometrically driven. We validate our analysis through experimentation, and present consistent improvement upon the MeshCNN baseline, as well as other more elaborate state-of-the-art architectures. Furthermore, we demonstrate this fundamental forms-based representation opens the door to accessible generative machine learning over meshes.

📄 PDF Abstract BibTeX arXiv:2105.13277

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Similar Papers 제목 키워드 기반

MedMeshCNN -- Enabling MeshCNN for Medical Surface Models

2020-09-10 · Lisa Schneider, Annika Niemann, Oliver Beuing, Bernhard Preim 외

Background and objective: MeshCNN is a recently proposed Deep Learning framework that drew attention due to its direct operation on irregular, non-uniform 3D meshes. On selected benchmarking datasets, it outperformed sta…

BenchmarkingSegmentation

MeshCNN: A Network with an Edge

2018-09-16 · Rana Hanocka, Amir Hertz, Noa Fish, Raja Giryes 외

Polygonal meshes provide an efficient representation for 3D shapes. They explicitly capture both shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate feature…

3D Object Classification3D Part SegmentationCube Engraving Classification

Geometric Deep Learning for Post-Menstrual Age Prediction based on the Neonatal White Matter Cortical Surface

2020-08-13 · Vitalis Vosylius, Andy Wang, Cemlyn Waters, Alexey Zakharov 외

Accurate estimation of the age in neonates is essential for measuring neurodevelopmental, medical, and growth outcomes. In this paper, we propose a novel approach to predict the post-menstrual age (PA) at scan, using tec…

Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentation

2022-08-08 · Ayaan Haque, Hankyu Moon, Heng Hao, Sima Didari 외

3D deep learning is a growing field of interest due to the vast amount of information stored in 3D formats. Triangular meshes are an efficient representation for irregular, non-uniform 3D objects. However, meshes are oft…

Contrastive LearningRepresentation LearningSegmentationSelf-Supervised Learning

Tailor Made Embeddings for Quantum Machine Learning

2026-06-24 · Aldo Lamarre, Dominik Šafránek arxiv

Autoencoders transformed classical machine learning by solving the curse of dimensionality, enabling principled weight initialization and learning compact, structured representations. In this work, we extend this paradig…

Quantum Machine Learning