Research map / 3D vision / Face and shape
ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model With Implicit Neural Representations
Mingwu Zheng, Haiyu Zhang, Hongyu Yang, Liming Chen, Di Huang
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 |
|---|---|---|---|
| add disentangled deformation fields (ablation) | ImFace++ · FaceScape ablation | Chamfer distance (mm): 0.568 -> 0.511 | Improved |
| add Neural Blend-Field (ablation) | ImFace++ · FaceScape ablation | Chamfer distance (mm): 0.564 -> 0.511 | Improved |
| add improved expression embedding learning (ablation) | ImFace++ · FaceScape ablation | Chamfer distance (mm): 0.596 -> 0.511 | Improved |
| add Refinement Displacement Field (ablation) | ImFace · FaceScape ablation | Chamfer distance (mm): 0.547 -> 0.511 | Improved |
| model displacement in aligned template space (ablation) | ImFace++ RDF · FaceScape ablation | Chamfer distance (mm): 0.536 -> 0.511 | Improved |
| use hyper net instead of concatenation (ablation) | ImFace++ · FaceScape ablation | Chamfer distance (mm): 0.526 -> 0.511 | Improved |
| use hyper net instead of adaptive normalization (ablation) | ImFace++ · FaceScape ablation | Chamfer distance (mm): 0.527 -> 0.511 | Improved |
| add landmark consistency loss (ablation) | ImFace++ · FaceScape ablation | Chamfer distance (mm): 0.518 -> 0.511 | Improved |
| add disentangled deformation fields (ablation) | ImFace++ · FaceScape ablation | F-score@1mm: 94.59 -> 96.11 | Improved |
| add Neural Blend-Field (ablation) | ImFace++ · FaceScape ablation | F-score@1mm: 93.41 -> 96.11 | Improved |
| add improved expression embedding learning (ablation) | ImFace++ · FaceScape ablation | F-score@1mm: 91.75 -> 96.11 | Improved |
| increase landmarks from 68 to 4,096 for consistency loss | ImFace · FaceScape correspondence | TDE (mm): 3.116 -> 1.620 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ImFace — ImFace: A Nonlinear 3D Morphable Face Model With Implicit Neural Representations (CVPR 2022) · better on 5 of 5 shared results
- i3DMM — i3DMM: Deep Implicit 3D Morphable Model of Human Heads (CVPR 2021) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ImFace: A Nonlinear 3D Morphable Face Model With Implicit Neural Representations (CVPR 2022 · similarity 0.97)
- A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces (TPAMI 2021 · similarity 0.91)
- ImHead: A Large-scale Implicit Morphable Model for Localized Head Modeling (ICCV 2025 · similarity 0.91)
- Learning Neural Parametric Head Models (CVPR 2023 · similarity 0.91)
- Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion (CVPR 2025 · similarity 0.89)
- 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024 · similarity 0.88)
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.
