CVJan 5, 2024

Partition-based Nonrigid Registration for 3D Face Model

arXiv:2401.02607v1h-index: 9
Originality Synthesis-oriented
AI Analysis

This is an incremental improvement for 3D face modeling, addressing large disparities between template and target models.

The paper tackles the problem of warping a handcrafted template model into captured models for 3D morphable models by proposing a partition-based surface registration method that partitions the template using landmarks, scales parts, and smooths boundaries, resulting in better performance than traditional warp methods and robustness to local minima.

This paper presents a partition-based surface registration for 3D morphable model(3DMM). In the 3DMM, it often requires to warp a handcrafted template model into different captured models. The proposed method first utilizes the landmarks to partition the template model then scale each part and finally smooth the boundaries. This method is especially effective when the disparity between the template model and the target model is huge. The experiment result shows the method perform well than the traditional warp method and robust to the local minima.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes