# Learning Skeletal Articulations with Neural Blend Shapes

arXiv: https://arxiv.org/abs/2105.02451 · HTML: https://mlsanity.com/paper/2105.02451/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 58 references that are in the map.
- First posted on arXiv 6 May 2021.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Multi-Garment Net: Learning to Dress 3D People from Images](https://mlsanity.com/paper/1908.06903/) (2019)
- [STAR: Sparse Trained Articulated Human Body Regressor](https://mlsanity.com/paper/2008.08535/) (2020)
- [Skeleton-Aware Networks for Deep Motion Retargeting](https://mlsanity.com/paper/2005.05732/) (2020)
- [Neural Cages for Detail-Preserving 3D Deformations](https://mlsanity.com/paper/1912.06395/) (2019)
- [Fast Tetrahedral Meshing in the Wild](https://mlsanity.com/paper/1908.03581/) (2019)
- [Accurate Face Rig Approximation with Deep Differential Subspace Reconstruction](https://mlsanity.com/paper/2006.01746/) (2020)
- [Complementary Dynamics](https://mlsanity.com/paper/2009.02462/) (2020)

## Built on by (most cited first, 30 of 53)

- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [ECON: Explicit Clothed humans Optimized via Normal integration](https://mlsanity.com/paper/2212.07422/) (2022)
- [TextDeformer: Geometry Manipulation using Text Guidance](https://mlsanity.com/paper/2304.13348/) (2023)
- [Fast Point Cloud Generation with Straight Flows](https://mlsanity.com/paper/2212.01747/) (2022)
- [RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets](https://mlsanity.com/paper/2502.09615/) (2025)
- [Image Sculpting: Precise Object Editing with 3D Geometry Control](https://mlsanity.com/paper/2401.01702/) (2024)
- [MagicArticulate: Make Your 3D Models Articulation-Ready](https://mlsanity.com/paper/2502.12135/) (2025)
- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [Controllable Mesh Generation Through Sparse Latent Point Diffusion Models](https://mlsanity.com/paper/2303.07938/) (2023)
- [Skeleton-free Pose Transfer for Stylized 3D Characters](https://mlsanity.com/paper/2208.00790/) (2022)
- [Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes](https://mlsanity.com/paper/2205.02904/) (2022)
- [TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision](https://mlsanity.com/paper/2303.13273/) (2023)
- [3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process](https://mlsanity.com/paper/2303.10406/) (2023)
- [Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters](https://mlsanity.com/paper/2411.18197/) (2024)
- [Morig: Motion-aware rigging of character meshes from point clouds](https://mlsanity.com/paper/2210.09463/) (2022)
- [iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos](https://mlsanity.com/paper/2506.08334/) (2025)
- [AniClipart: Clipart Animation with Text-to-Video Priors](https://mlsanity.com/paper/2404.12347/) (2024)
- [SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters](https://mlsanity.com/paper/2203.04746/) (2022)
- [TapMo: Shape-aware Motion Generation of Skeleton-free Characters](https://mlsanity.com/paper/2310.12678/) (2023)
- [Patch-based 3D Natural Scene Generation from a Single Example](https://mlsanity.com/paper/2304.12670/) (2023)
- [Zero-shot Pose Transfer for Unrigged Stylized 3D Characters](https://mlsanity.com/paper/2306.00200/) (2023)
- [HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset](https://mlsanity.com/paper/2412.02317/) (2024)
- [ChatHuman: Chatting about 3D Humans with Tools](https://mlsanity.com/paper/2405.04533/) (2024)
- [Temporal Residual Jacobians For Rig-free Motion Transfer](https://mlsanity.com/paper/2407.14958/) (2024)
- [HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting](https://mlsanity.com/paper/2303.10941/) (2023)
- [VINECS: Video-based Neural Character Skinning](https://mlsanity.com/paper/2307.00842/) (2023)
- [Robust Biharmonic Skinning Using Geometric Fields](https://mlsanity.com/paper/2406.00238/) (2024)
- [SMF: Template-free and Rig-free Animation Transfer using Kinetic Codes](https://mlsanity.com/paper/2504.04831/) (2025)
- [PoissonNet: A Local-Global Approach for Learning on Surfaces](https://mlsanity.com/paper/2510.14146/) (2025)
- [Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation](https://mlsanity.com/paper/2407.11266/) (2024)

## Abstract (arXiv)

Animating a newly designed character using motion capture (mocap) data is a long standing problem in computer animation. A key consideration is the skeletal structure that should correspond to the available mocap data, and the shape deformation in the joint regions, which often requires a tailored, pose-specific refinement. In this work, we develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure which produces high quality pose dependent deformations. Our framework learns to rig and skin characters with the same articulation structure (e.g., bipeds or quadrupeds), and builds the desired skeleton hierarchy into the network architecture. Furthermore, we propose neural blend shapes--a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning. Our system estimates neural blend shapes for input meshes with arbitrary connectivity, as well as weighting coefficients which are conditioned on the input joint rotations. Unlike recent deep learning techniques which supervise the network with ground-truth rigging and skinning parameters, our approach does not assume that the training data has a specific underlying deformation model. Instead, during training, the network observes deformed shapes and learns to infer the corresponding rig, skin and blend shapes using indirect supervision. During inference, we demonstrate that our network generalizes to unseen characters with arbitrary mesh connectivity, including unrigged characters built by 3D artists. Conforming to standard skeletal animation models enables direct plug-and-play in standard animation software, as well as game engines.