Research map / 3D vision / Face and shape
Towards Fine-Grained Optimal 3D Face Dense Registration: An Iterative Dividing and Diffusing Method
Zhenfeng Fan, Silong Peng, Shihong Xia
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| apply dividing and diffusing optimization after E-NICP | E-NICP registrations · FaceScape (16,900 samples) | global local-scaling metric: 0.061 -> 0.044 | Improved |
| apply dividing and diffusing optimization after NICP | NICP registrations · BU-3DFE (2,500 samples) | global local-scaling metric: 0.058 -> 0.042 | Improved |
| apply dividing and diffusing optimization after LSD | LSD registrations · BU-3DFE (2,500 samples) | global local-scaling metric: 0.055 -> 0.041 | Improved |
| use multi-resolution version instead of full resolution (ablation) | dividing and diffusing · FaceScape (16,900 samples) | global local-scaling metric: 0.044 -> 0.045 | No clear effect |
| add multi-resolution scheme (ablation) | dividing and diffusing · Runtime, model with 26,317 vertices | average time (s): 13.56s -> 5.85s | Improved |
| add multi-resolution scheme (ablation) | dividing and diffusing · 1D line segmentation toy example | iterations to converge: 18 -> 2 iterations | Improved |
| apply dividing and diffusing to E-NICP training samples | FaceScape PCA model · FaceScape PCA model (first 20 components) | variance explained (compactness): 90.38% -> 91.19% | Improved |
| apply dividing and diffusing to training samples | FaceScape PCA model · FaceScape test set | generalization error: reduced notably (no numbers given) | Improved |
| apply dividing and diffusing to training samples | FaceScape PCA model · FaceScape test set | specificity error: smaller specificity error (no numbers given) | Improved |
Closest papers by meaning
- Dense 3D Face Correspondence (TPAMI 2017 · similarity 0.91)
- Boosting Local Shape Matching for Dense 3D Face Correspondence (CVPR 2019 · similarity 0.90)
- Dense Semantic and Topological Correspondence of 3D Faces without Landmarks (ECCV 2018 · similarity 0.89)
- A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces (TPAMI 2021 · similarity 0.88)
- Functional Faces: Groupwise Dense Correspondence Using Functional Maps (CVPR 2016 · similarity 0.87)
- 3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
