Research map / Video / Video generation
EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis
Shuai Tan, Bin Ji, Ye Pan
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 |
|---|---|---|---|
| increase mouth bank size from 5 to 20 bases (ablation) | EDTalk++ · MEAD | PSNR: 20.39 -> 22.42 | Improved |
| increase mouth bank size from 20 to 40 bases (ablation) | EDTalk++ · MEAD | PSNR: 22.42 -> 20.79 | Hurt |
| increase expression bank size from 5 to 10 bases (ablation) | EDTalk++ · MEAD | Acc_emo: 53.26 -> 68.21 | Improved |
| increase expression bank size from 10 to 20 bases (ablation) | EDTalk++ · MEAD | Acc_emo: 68.21 -> 61.34 | Hurt |
| add base banks (ablation) | EDTalk++ · MEAD | disentanglement quality | Improved |
| add orthogonal constraint on bases (ablation) | EDTalk++ · MEAD | emotion expressiveness | Improved |
| upgrade EDTalk to EDTalk++ | EDTalk · MEAD | FID: 17.698 -> 15.679 | Improved |
| upgrade EDTalk to EDTalk++ | EDTalk · MEAD | Acc_emo: 67.32 -> 68.21 | Improved |
| upgrade EDTalk to EDTalk++ | EDTalk · HDTF | PSNR: 25.156 -> 25.914 | Improved |
| upgrade EDTalk to EDTalk++ | EDTalk · Voxceleb2 | M-LMD: 1.851 -> 1.831 | Improved |
| upgrade EDTalk to EDTalk++ | EDTalk · MEAD | Sync_conf: 8.115 -> 8.036 | Mixed |
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.
- EDTalk — EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis (ECCV 2024) · better on 5 of 5 shared results
- StyleTalk — StyleTalk: One-Shot Talking Head Generation with Controllable Speaking Styles (AAAI 2023) · better on 3 of 3 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
- EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion (CVPR 2025 · similarity 0.92)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.91)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.91)
- FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio (CVPR 2024 · similarity 0.90)
- MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation (AAAI 2025 · similarity 0.90)
- AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation (AAAI 2025 · similarity 0.89)
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.
