Research map / Video / Video generation
InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars
Quanyue Song, Yishan He, Guo Zhi, yanfei zhang, Shihao Cheng, Zhixiang He, Chi Zhang, Caigui Jiang, Xuelong Li
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 long-term memory in LSVM (ablation) | InteractiveAvatar · Interactive avatar ablation | OBJ: 82.6 -> 85.2 | Improved |
| replace random key-frame sampling with Dynamic Key-Frame Selection (ablation) | InteractiveAvatar · Interactive avatar ablation | OBJ: 83.1 -> 85.2 | Improved |
| add full LSVM module (ablation) | InteractiveAvatar · Interactive avatar ablation | OBJ: 78.4 -> 85.2 | Improved |
| add full LSVM module (ablation) | InteractiveAvatar · Interactive avatar ablation | FPS: 30.04 -> 26.68 | Hurt |
| add State-Cycling strategy (ablation) | InteractiveAvatar · Interactive avatar ablation | TV: 25.42 -> 25.93 | Improved |
| add Cache-Switching (ablation) | InteractiveAvatar · Interactive avatar ablation | OBJ: 84.5 -> 85.2 | Improved |
| add Reasoning-Reaction Module (ablation) | InteractiveAvatar · Interactive avatar ablation | TV: 24.89 -> 25.93 | Improved |
| add DMD distillation (ablation) | InteractiveAvatar · Interactive avatar ablation | FPS: 1.27 -> 26.68 | Improved |
| use InteractiveAvatar instead of LiveAvatar | InteractiveAvatar · Interactive avatar test set (500 videos) | FPS: 21.94 -> 26.68 | Improved |
| use InteractiveAvatar instead of HYAvatar | InteractiveAvatar · Interactive avatar test set (500 videos) | FVD: 632.6 -> 701.4 | Hurt |
Closest papers by meaning
- InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation (AAAI 2025 · similarity 0.86)
- RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control (CVPR 2024 · similarity 0.85)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.85)
- Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory (NeurIPS 2026 · similarity 0.84)
- VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis (CVPR 2025 · similarity 0.84)
- X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation (ICML 2024 · similarity 0.84)
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.
