Research map / 3D vision / Face and shape
3DCaricShop: A Dataset and a Baseline Method for Single-View 3D Caricature Face Reconstruction
Yuda Qiu, Xiaojie Xu, Lingteng Qiu, Yan Pan, Yushuang Wu, Weikai Chen, Xiaoguang Han
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 |
|---|---|---|---|
| Combine implicit reconstruction with landmark-guided template registration and PCA projection | 3DCaricShop reconstruction · 3DCaricShop test set, face reconstruction | P2S: 0.126 -> 0.037 | Improved |
| Add GCN refinement to projected 2D landmarks (ablation) | 3DCaricShop landmark detector · 3DCaricShop test set, landmark detection | MPJPE: 0.451 -> 0.291 | Improved |
| Use the proposed detector instead of voxel-based 3D heatmap estimation (ablation) | 3DCaricShop landmark detector · 3DCaricShop test set, landmark detection | MPJPE: 0.407 -> 0.291 | Improved |
| Add view-collaborative GCN blocks rather than using a global graph alone (ablation) | 3DCaricShop landmark detector · 3DCaricShop test set, landmark detection | MPJPE: 0.373 -> 0.291 | Improved |
| Add non-local global-to-local feature enhancement (ablation) | 3DCaricShop landmark detector · 3DCaricShop test set, landmark detection | MPJPE: 0.358 -> 0.291 | Improved |
| Add landmark guidance to NICP registration (ablation) | 3DCaricShop registration · 3DCaricShop test set, registration | P2S: 0.074 -> 0.065 | Improved |
| Add PCA projection after landmark-guided NICP (ablation) | 3DCaricShop registration · 3DCaricShop test set, registration | P2S: 0.076 -> 0.065 | Improved |
Closest papers by meaning
- Alive Caricature From 2D to 3D (CVPR 2018 · similarity 0.90)
- CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo Booth (CVPR 2025 · similarity 0.87)
- Learning to Caricature via Semantic Shape Transform (IJCV 2021 · similarity 0.87)
- Topologically Consistent Multi-View Face Inference Using Volumetric Sampling (ICCV 2021 · similarity 0.86)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.85)
- LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example (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.
