ASM: Adaptive Skinning Model for High-Quality 3D Face Modeling
This work addresses the need for high-capacity face models in multi-view reconstruction, facilitating applications like avatar creation, though it appears incremental by shifting focus from data-dependent to human-designed models.
The authors tackled the problem of tailoring parametric face models for multi-view uncalibrated image reconstruction by proposing the Adaptive Skinning Model (ASM), which achieves state-of-the-art performance on the Florence MICC Coop benchmark with improved capacity and smaller model size compared to 3D Morphable Models.
The research fields of parametric face model and 3D face reconstruction have been extensively studied. However, a critical question remains unanswered: how to tailor the face model for specific reconstruction settings. We argue that reconstruction with multi-view uncalibrated images demands a new model with stronger capacity. Our study shifts attention from data-dependent 3D Morphable Models (3DMM) to an understudied human-designed skinning model. We propose Adaptive Skinning Model (ASM), which redefines the skinning model with more compact and fully tunable parameters. With extensive experiments, we demonstrate that ASM achieves significantly improved capacity than 3DMM, with the additional advantage of model size and easy implementation for new topology. We achieve state-of-the-art performance with ASM for multi-view reconstruction on the Florence MICC Coop benchmark. Our quantitative analysis demonstrates the importance of a high-capacity model for fully exploiting abundant information from multi-view input in reconstruction. Furthermore, our model with physical-semantic parameters can be directly utilized for real-world applications, such as in-game avatar creation. As a result, our work opens up new research direction for parametric face model and facilitates future research on multi-view reconstruction.