Research map / Video / Video generation
SyncDreamer: Controllable and Expressive Avatar Generation Beyond the Talking Head
Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia, Josef Kittler, Muhammad Awais
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 Attention Localization Loss on visual cross-attention (ablation) | SyncDreamer · qualitative ablation | identity and spatial consistency | Improved |
| add Audio Dynamics Encoder (temporal reweighting of Wav2Vec2 features) (ablation) | SyncDreamer · expressive and non-verbal audio, qualitative | expression and sync quality | Improved |
| use automatically enhanced prompts instead of minimal user prompts (ablation) | SyncDreamer · upper-body prompt control, qualitative | gesture and object continuity | Improved |
| use automatically enhanced prompts instead of manually enriched prompts (ablation) | SyncDreamer · upper-body prompt control, qualitative | gesture expressiveness and coherence | Improved |
| use SyncDreamer instead of OmniAvatar | audio-driven avatar generation · HDTF | FID: 53.7 -> 52.8 | Improved |
| use SyncDreamer instead of OmniAvatar | audio-driven avatar generation · AVSpeech | Sync-D: 6.73 -> 7.05 | Hurt |
| use SyncDreamer instead of pose-driven EchoMimicV2 | upper-body avatar generation · EMTD | CSIM: 0.393 -> 0.598 | Improved |
| use SyncDreamer instead of EchoMimicV2 | upper-body avatar generation · EMTD | FVD: 528.10 -> 483.59 | Improved |
| give baseline models the enhanced motion prompts | DiT baselines (Hallo3, HunyuanVideo Avatar, OmniAvatar, FantasyTalk) · upper-body qualitative | gesture and gaze alignment | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- Hallo3 — Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer (CVPR 2025) · better on 1 of 1 shared result
- MimicMotion — MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance (ICML 2025) · better on 1 of 1 shared result
- AnimateAnyone — Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (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
- InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation (AAAI 2025 · similarity 0.91)
- FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization (CVPR 2024 · similarity 0.90)
- Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style (AAAI 2024 · similarity 0.89)
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (AAAI 2025 · similarity 0.89)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.88)
- EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion (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.
