paper-with-me

홈 › Papers

A Graph Neural Network Approach for Temporal Mesh Blending and Correspondence

2023-06-23 · Aalok Gangopadhyay, Abhinav Narayan Harish, Prajwal Singh, Shanmuganathan Raman

We have proposed a self-supervised deep learning framework for solving the mesh blending problem in scenarios where the meshes are not in correspondence. To solve this problem, we have developed Red-Blue MPNN, a novel graph neural network that processes an augmented graph to estimate the correspondence. We have designed a novel conditional refinement scheme to find the exact correspondence when certain conditions are satisfied. We further develop a graph neural network that takes the aligned meshes and the time value as input and fuses this information to process further and generate the desired result. Using motion capture datasets and human mesh designing software, we create a large-scale synthetic dataset consisting of temporal sequences of human meshes in motion. Our results demonstrate that our approach generates realistic deformation of body parts given complex inputs.

📄 PDF Abstract BibTeX arXiv:2306.13452

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural NetworkTemporal Sequences

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음
MPNN There are at least eight notable examples of models from the literature that can be described using the Message Passing Neural Networks (MPNN) framework. For simplicity we…

Similar Papers 제목 키워드 기반

Ultron: Enabling Temporal Geometry Compression of 3D Mesh Sequences using Temporal Correspondence and Mesh Deformation

2024-09-08 · Haichao Zhu

With the advancement of computer vision, dynamic 3D reconstruction techniques have seen significant progress and found applications in various fields. However, these techniques generate large amounts of 3D data sequences…

3D ReconstructionModel Compression

Fast 4D Mesh Generation by Spatio-Temporal Attention Chains

2026-05-19 · Dvir Samuel, Yuval Atzmon, Gal Chechik, Yoni Kasten arxiv

4D mesh generation has recently emerged as a powerful paradigm for recovering dynamic 3D structure from videos, but existing methods remain slow, computationally expensive, and difficult to scale to longer sequences. We …

Object Tracking

DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction

2024-03-18 · Yuxin Yao, Siyu Ren, Junhui Hou, Zhi Deng 외

This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning fram…

Surface Reconstruction

DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation

2024-10-09 · Zhiqi Li, Yiming Chen, Peidong Liu

Recent advancements in 2D/3D generative techniques have facilitated the generation of dynamic 3D objects from monocular videos. Previous methods mainly rely on the implicit neural radiance fields (NeRF) or explicit Gauss…

3D GenerationComputational EfficiencyImage to 3DNeRF

Dual Mesh Convolutional Networks for Human Shape Correspondence

2021-03-23 · Nitika Verma, Adnane Boukhayma, Jakob Verbeek, Edmond Boyer

Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids. The transposition to meshes is, however, not straight-forward due to their irregular structure. We e…

3D Shape Representation