Research map / 3D vision / Face and shape
Boosting Local Shape Matching for Dense 3D Face Correspondence
Zhenfeng Fan, Xiyuan Hu, Chen Chen, Silong Peng
Check 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 |
|---|---|---|---|
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 outer eye corner (Ex) · FRGC v2.0 | landmark localization error (mm; mean): 2.5 -> 2.1 | Improved |
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 inner eye corner (En) · FRGC v2.0 | landmark localization error (mm; mean): 2.4 -> 1.9 | Improved |
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 nose bridge saddle (N) · FRGC v2.0 | landmark localization error (mm; mean): 2.4 -> 2.4 | No clear effect |
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 nose tip (Prn) · FRGC v2.0 | landmark localization error (mm; mean): 2.1 -> 1.8 | Improved |
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 nasal base (Sn) · FRGC v2.0 | landmark localization error (mm; mean): 2.7 -> 1.8 | Improved |
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 nose corner (Ac) · FRGC v2.0 | landmark localization error (mm; mean): 2.6 -> 1.9 | Improved |
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 mouth corner (Ch) · FRGC v2.0 | landmark localization error (mm; mean): 2.5 -> 2.8 | Hurt |
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 upper lip midpoint (Ls) · FRGC v2.0 | landmark localization error (mm; mean): 2.4 -> 2.0 | Improved |
| Use the proposed dense correspondence method rather than the strongest listed baseline | FRGC v2.0 lower lip midpoint (Li) · FRGC v2.0 | landmark localization error (mm; mean): 3.5 -> 4.3 | Hurt |
| Fit correspondence with the proposed method instead of NICP or the BFM model | PCA model of 200 corresponded samples · Collected high-resolution face database | principal components needed to explain 99% energy: 59(63) -> 43 | Improved |
Closest papers by meaning
- Dense 3D Face Correspondence (TPAMI 2017 · similarity 0.91)
- Dense Semantic and Topological Correspondence of 3D Faces without Landmarks (ECCV 2018 · similarity 0.90)
- Towards Fine-Grained Optimal 3D Face Dense Registration: An Iterative Dividing and Diffusing Method (IJCV 2023 · similarity 0.90)
- A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces (TPAMI 2021 · similarity 0.89)
- Probabilistic Deformation Consistency for Unsupervised Shape Matching (AAAI 2026 · similarity 0.87)
- Unsupervised Learning of Dense Shape Correspondence (CVPR 2019 · similarity 0.87)
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.
