# High-fidelity Interpretable Inverse Rig: An Accurate and Sparse Solution Optimizing the Quartic Blendshape Model

arXiv: https://arxiv.org/abs/2302.04820 · HTML: https://mlsanity.com/paper/2302.04820/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 57 references that are in the map.
- First posted on arXiv 9 Feb 2023.

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

- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [Coordinate Descent Algorithms](https://mlsanity.com/paper/1502.04759/) (2015)
- [Deep Appearance Models for Face Rendering](https://mlsanity.com/paper/1808.00362/) (2018)
- [Coordinate Descent Converges Faster with the Gauss-Southwell Rule Than Random Selection](https://mlsanity.com/paper/1506.00552/) (2015)
- [Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting](https://mlsanity.com/paper/2007.06759/) (2020)
- [HeadOn: Real-time Reenactment of Human Portrait Videos](https://mlsanity.com/paper/1805.11729/) (2018)
- [Accurate Face Rig Approximation with Deep Differential Subspace Reconstruction](https://mlsanity.com/paper/2006.01746/) (2020)
- [Clustering of the Blendshape Facial Model](https://mlsanity.com/paper/2110.15313/) (2021)
- [A Majorization-Minimization Based Method for Nonconvex Inverse Rig Problems in Facial Animation: Algorithm Derivation](https://mlsanity.com/paper/2205.04289/) (2022)
- [Rig Inversion by Training a Differentiable Rig Function](https://mlsanity.com/paper/2301.09567/) (2023)

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

- [Distributed Solution of the Inverse Rig Problem in Blendshape Facial Animation](https://mlsanity.com/paper/2303.06370/) (2023)

## Abstract (arXiv)

We propose a method to fit arbitrarily accurate blendshape rig models by solving the inverse rig problem in realistic human face animation. The method considers blendshape models with different levels of added corrections and solves the regularized least-squares problem using coordinate descent, i.e., iteratively estimating blendshape weights. Besides making the optimization easier to solve, this approach ensures that mutually exclusive controllers will not be activated simultaneously and improves the goodness of fit after each iteration. We show experimentally that the proposed method yields solutions with mesh error comparable to or lower than the state-of-the-art approaches while significantly reducing the cardinality of the weight vector (over 20 percent), hence giving a high-fidelity reconstruction of the reference expression that is easier to manipulate in the post-production manually. Python scripts for the algorithm will be publicly available upon acceptance of the paper.