GNPM: Geometric-Aware Neural Parametric Models
Not on the map. Why?
Abstract (arXiv)
We propose Geometric Neural Parametric Models (GNPM), a learned parametric model that takes into account the local structure of data to learn disentangled shape and pose latent spaces of 4D dynamics, using a geometric-aware architecture on point clouds. Temporally consistent 3D deformations are estimated without the need for dense correspondences at training time, by exploiting cycle consistency. Besides its ability to learn dense correspondences, GNPMs also enable latent-space manipulations such as interpolation and shape/pose transfer. We evaluate GNPMs on various datasets of clothed humans, and show that it achieves comparable performance to state-of-the-art methods that require dense correspondences during training.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 17 of its 34 references that are in the map. First posted on arXiv 21 Sep 2022.
Builds on
17 of 34 references.
References · 17
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
- 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 312
- 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
- 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
- 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 181
- 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 124
- 2020LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registrationcited by 108
- 2020Kernel Operations on the GPU, with Autodiff, without Memory Overflowscited by 104
5 more
- 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
- 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 90
- 2021NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Gocited by 81
- 2020Neural Deformation Graphs for Globally-consistent Non-rigid Reconstructioncited by 67
- 2019Combining 3D Morphable Models: A Large scale Face-and-Head Modelcited by 49
Built on by
Citing papers per year: 2023: 2; 2024: 1.
3 papers.