# CageNet: A Meta-Framework for Learning on Wild Meshes

arXiv: https://arxiv.org/abs/2505.18772 · HTML: https://mlsanity.com/paper/2505.18772/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 76 references that are in the map.
- First posted on arXiv 24 May 2025.

## Builds on (most cited first, 30 of 30)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [DiffusionNet: Discretization Agnostic Learning on Surfaces](https://mlsanity.com/paper/2012.00888/) (2020)
- [Learning shape correspondence with anisotropic convolutional neural networks](https://mlsanity.com/paper/1605.06437/) (2016)
- [SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator](https://mlsanity.com/paper/1911.05856/) (2019)
- [Deforming Radiance Fields with Cages](https://mlsanity.com/paper/2207.12298/) (2022)
- [Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations](https://mlsanity.com/paper/2205.02825/) (2022)
- [MeshCNN: A Network with an Edge](https://mlsanity.com/paper/1809.05910/) (2018)
- [Subdivision-Based Mesh Convolution Networks](https://mlsanity.com/paper/2106.02285/) (2021)
- [Deep Geometric Texture Synthesis](https://mlsanity.com/paper/2007.00074/) (2020)
- [KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control](https://mlsanity.com/paper/2104.11224/) (2021)
- [Neural Subdivision](https://mlsanity.com/paper/2005.01819/) (2020)
- [Primal-Dual Mesh Convolutional Neural Networks](https://mlsanity.com/paper/2010.12455/) (2020)
- [CNNs on Surfaces using Rotation-Equivariant Features](https://mlsanity.com/paper/2006.01570/) (2020)
- [A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes](https://mlsanity.com/paper/1809.06664/) (2018)
- [ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soups](https://mlsanity.com/paper/2005.11621/) (2020)
- [Fast Tetrahedral Meshing in the Wild](https://mlsanity.com/paper/1908.03581/) (2019)
- [Multi-directional Geodesic Neural Networks via Equivariant Convolution](https://mlsanity.com/paper/1810.02303/) (2018)
- [RigNet: Neural Rigging for Articulated Characters](https://mlsanity.com/paper/2005.00559/) (2020)
- [MeshWalker: Deep Mesh Understanding by Random Walks](https://mlsanity.com/paper/2006.05353/) (2020)
- [Surface Networks via General Covers](https://mlsanity.com/paper/1812.10705/) (2018)
- [SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters](https://mlsanity.com/paper/2203.04746/) (2022)
- [Continuous Geodesic Convolutions for Learning on 3D Shapes](https://mlsanity.com/paper/2002.02506/) (2020)
- [HodgeNet: Learning Spectral Geometry on Triangle Meshes](https://mlsanity.com/paper/2104.12826/) (2021)
- [HeterSkinNet: A Heterogeneous Network for Skin Weights Prediction](https://mlsanity.com/paper/2103.10602/) (2021)
- [SieveNet: Selecting Point-Based Features for Mesh Networks](https://mlsanity.com/paper/2308.12530/) (2023)

## Built on by (most cited first, 1 of 1)

- [Gauge-Equivariant Attention for Rotation-Stable 360^circ Scene Understanding](https://mlsanity.com/paper/2609.31755/) (2026)

## Abstract (arXiv)

Learning on triangle meshes has recently proven to be instrumental to a myriad of tasks, from shape classification, to segmentation, to deformation and animation, to mention just a few. While some of these applications are tackled through neural network architectures which are tailored to the application at hand, many others use generic frameworks for triangle meshes where the only customization required is the modification of the input features and the loss function. Our goal in this paper is to broaden the applicability of these generic frameworks to "wild", i.e. meshes in-the-wild which often have multiple components, non-manifold elements, disrupted connectivity, or a combination of these. We propose a configurable meta-framework based on the concept of caged geometry: Given a mesh, a cage is a single component manifold triangle mesh that envelopes it closely. Generalized barycentric coordinates map between functions on the cage, and functions on the mesh, allowing us to learn and test on a variety of data, in different applications. We demonstrate this concept by learning segmentation and skinning weights on difficult data, achieving better performance to state of the art techniques on wild meshes.