Research map / 3D vision / Face and shape
Expressive Talking Human from Single-Image with Imperfect Priors
Jun Xiang, Yudong Guo, Leipeng Hu, Boyang Guo, Yancheng Yuan, Juyong Zhang
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 mesh-related soft constraints (ablation) | Full model · Self-driven reenactment (ablation) | PSNR: 27.99 -> 29.31 | Improved |
| use LPIPS perceptual guidance instead of L1&SSIM on pseudo-frames (ablation) | Full model · Self-driven reenactment (ablation) | PSNR: 28.40 -> 29.31 | Improved |
| add re-tracking of pseudo-frames (ablation) | Full model · Self-driven reenactment (ablation) | PSNR: 27.99 -> 29.31 | Improved |
| add pseudo face supervision (ablation) | Full model · Self-driven reenactment (ablation) | PSNR: 28.24 -> 29.31 | Improved |
| add pseudo face supervision (ablation) | Full model · Self-driven reenactment (ablation) | LPIPS: 0.0293 -> 0.0299 | No clear effect |
| add LPIPS perceptual guidance instead of L1&SSIM (ablation) | Full model · Self-driven reenactment (ablation) | LPIPS: 0.0347 -> 0.0299 | Improved |
| one-shot Ours versus StableAnimator | Ours · Self-driven reenactment (one-shot input) | PSNR: 27.350 -> 29.311 | Improved |
| one-shot Ours versus ExAvatar 40-shot video input | Ours · Self-driven reenactment (one-shot input) | LPIPS: 0.0409 -> 0.0299 | Improved |
Closest papers by meaning
- Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis (ICLR 2024 · similarity 0.90)
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation (CVPR 2024 · similarity 0.89)
- From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations (CVPR 2024 · similarity 0.89)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.88)
- Expressive Gaussian Human Avatars from Monocular RGB Video (NeurIPS 2024 · similarity 0.88)
- VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis (CVPR 2025 · 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.
