Research map / 3D vision / Face and shape
Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation
Taekyung Ki, Dongchan Min, Gyeongsu Chae
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 contrastive pre-training (CLeBS) instead of raw 3DMM expression injection (ablation) | Export3D · VFHQ cross-identity | CSIM: 0.648 -> 0.694 | Improved |
| add contrastive pre-training instead of end-to-end LeBS (n=10) (ablation) | Export3D · VFHQ same-identity | AED: 0.110 -> 0.082 | Improved |
| reduce number of basis vectors n in end-to-end LeBS from 25 to 5 (ablation) | E2E LeBS · VFHQ same-identity | CSIM: 0.745 -> 0.658 | Hurt |
| use EAdaLN instead of cross-attention for expression conditioning (ablation) | Export3D generator · VFHQ same-identity | CSIM: 0.678 -> 0.811 | Improved |
| use EAdaLN instead of cross-attention (ablation) | Export3D generator · VFHQ cross-identity | AED: 0.271 -> 0.208 | Improved |
| Export3D vs HiDe-NeRF identity preservation | Export3D · VFHQ same-identity | CSIM: 0.867 -> 0.811 | Hurt |
| Export3D vs DPE on structural similarity | Export3D · VFHQ same-identity | SSIM: 0.750 -> 0.704 | Hurt |
| Gaussian low-pass filter after pixel shuffle upsampling | tri-plane generator · qualitative | grid artifacts | Improved |
Closest papers by meaning
- DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis (CVPR 2024 · similarity 0.89)
- RealPortrait: Realistic Portrait Animation with Diffusion Transformers (AAAI 2025 · similarity 0.86)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.86)
- Coherent 3D Portrait Video Reconstruction via Triplane Fusion (CVPR 2025 · similarity 0.86)
- Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer (CVPR 2025 · similarity 0.85)
- Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis (ICLR 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.
