paper-with-me

홈 › Papers

Differentiable Voxelization and Mesh Morphing

2024-07-15 · Yihao Luo, Yikai Wang, Zhengrui Xiang, Yuliang Xiu, Guang Yang, ChoonHwai Yap

In this paper, we propose the differentiable voxelization of 3D meshes via the winding number and solid angles. The proposed approach achieves fast, flexible, and accurate voxelization of 3D meshes, admitting the computation of gradients with respect to the input mesh and GPU acceleration. We further demonstrate the application of the proposed voxelization in mesh morphing, where the voxelized mesh is deformed by a neural network. The proposed method is evaluated on the ShapeNet dataset and achieves state-of-the-art performance in terms of both accuracy and efficiency.

📄 PDF Abstract BibTeX arXiv:2407.11272

Code (2)

luo-yihao/doph 공식 구현 pytorch
luo-yihao/ghdheart 공식 구현 pytorch

Tasks

GPU

Similar Papers 제목 키워드 기반

Explicit Differentiable Slicing and Global Deformation for Cardiac Mesh Reconstruction

2024-09-03 · Yihao Luo, Dario Sesia, Fanwen Wang, Yinzhe Wu 외

Mesh reconstruction of the cardiac anatomy from medical images is useful for shape and motion measurements and biophysics simulations to facilitate the assessment of cardiac function and health. However, 3D medical image…

Anatomy

Parametric shape models for vessels learned from segmentations via differentiable voxelization

2025-07-03 · Alina F. Dima, Suprosanna Shit, Huaqi Qiu, Robbie Holland 외 arxiv

Vessels are complex structures in the body that have been studied extensively in multiple representations. While voxelization is the most common of them, meshes and parametric models are critical in various applications …

SemMorph3D: Unsupervised Semantic-Aware 3D Morphing via Mesh-Guided Gaussians

2025-10-02 · Mengtian Li, Yunshu Bai, Yimin Chu, Xinru Guo 외 arxiv

We introduce METHODNAME, a novel framework for semantic-aware 3D shape and texture morphing directly from multi-view images. While 3D Gaussian Splatting (3DGS) enables photorealistic rendering, its unstructured nature of…

Semantic correspondence

Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression

2025-08-03 · Wanhao Ma, Wei Zhang, Shuai Wan, Fuzheng Yang arxiv

Geometry-based point cloud compression (G-PCC), an international standard designed by MPEG, provides a generic framework for compressing diverse types of point clouds while ensuring interoperability across applications a…

Point Clouds

Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes

2022-05-05 · Noam Aigerman, Kunal Gupta, Vladimir G. Kim, Siddhartha Chaudhuri 외

This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not s…