Research map / Video / Video generation
Pixel-Perfect Puppetry: Precision-Guided Enhancement for Face Image and Video Editing
Yan Li, Zhenyi Wang, Guanghao Li, Wei Xue, Wenhan Luo, Yike Guo
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 |
|---|---|---|---|
| remove Implicit Basis Guidance (keep LBE) (ablation) | FlowGuide · HDTF ablation (Smile/Mustache) | IPR / TG-ID: IPR 0.9510 -> 0.9370; TG-ID 0.9929 -> 0.8854 | Hurt |
| remove Latent Basis Extraction (ablation) | FlowGuide · HDTF ablation (Smile/Mustache) | CLIP-Score / TG-ID: IPR 0.9510 -> 0.9831; CLIP 0.7563 -> 0.7437; TG-ID 0.9929 -> 0.9775 | Mixed |
| remove both LBE and IBG (ablation) | FlowGuide · HDTF ablation (Smile/Mustache) | IPR / TG-ID: IPR 0.9510 -> 0.8790; TG-ID 0.9929 -> 0.8557 | Hurt |
| use Pearson correlation instead of cosine similarity for guidance (ablation) | FlowGuide · CelebA face image editing (500 images) | PSNR: 23.160 -> 16.988 | Hurt |
| use Spearman correlation instead of cosine similarity (ablation) | FlowGuide · CelebA face image editing (500 images) | PSNR / CLIP Sim: PSNR 23.160 -> 24.129; CLIP Sim 19.391 -> 17.831 | Mixed |
| FlowGuide (cosine) vs h-Edit | Face image editing · CelebA face image editing (500 images) | PSNR / CLIP Sim: PSNR 22.078 -> 23.160; CLIP Sim 19.707 -> 19.391 | Mixed |
| FlowGuide vs strongest video baseline on identity | Face video editing · HDTF face video editing (Smile/Mustache mean) | Identity Preservation Rate: 0.9413 (TCSVE) -> 0.9667 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RAVE — RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models (CVPR 2024) · better on 1 of 1 shared result
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
- A Latent Transformer for Disentangled Face Editing in Images and Videos (ICCV 2021 · similarity 0.89)
- DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation (CVPR 2024 · similarity 0.88)
- Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement (ICLR 2026 · similarity 0.87)
- When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation (CVPR 2024 · similarity 0.87)
- FlowFace: Rectifying Identity Conditioning with Riemannian Geometry for Face Generation (ECCV 2026 · similarity 0.87)
- SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing (NeurIPS 2025 · similarity 0.86)
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.
