Research map / Video / Video generation
EgoTwin: Dreaming Body and View in First Person
Jingqiao Xiu, Fangzhou Hong, Yicong Li, Mengze Li, Wentao Wang, Sirui Han, Liang Pan, Ziwei Liu
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 head-centric Motion Reformulation (ablation) | EgoTwin · Nymeria test | FVD: 1356.81 -> 1033.52 | Improved |
| add head-centric Motion Reformulation (ablation) | EgoTwin · Nymeria test | HandScore: 0.44 -> 0.81 | Improved |
| add head-centric Motion Reformulation (ablation) | EgoTwin · Nymeria test | RotErr: 1.22 -> 0.46 | Improved |
| add head-centric Motion Reformulation (ablation) | EgoTwin · Nymeria test | I-FID: 134.27 -> 98.17 | Improved |
| add the cybernetics-inspired Interaction Mechanism (masked attention) (ablation) | EgoTwin · Nymeria test | FVD: 1237.58 -> 1033.52 | Improved |
| add the cybernetics-inspired Interaction Mechanism (masked attention) (ablation) | EgoTwin · Nymeria test | HandScore: 0.57 -> 0.81 | Improved |
| add the cybernetics-inspired Interaction Mechanism (masked attention) (ablation) | EgoTwin · Nymeria test | RotErr: 0.89 -> 0.46 | Improved |
| add the cybernetics-inspired Interaction Mechanism (masked attention) (ablation) | EgoTwin · Nymeria test | I-FID: 117.54 -> 98.17 | Improved |
| add Asynchronous Diffusion with dedicated sampling (ablation) | EgoTwin · Nymeria test | FVD: 1124.19 -> 1033.52 | Improved |
| add Asynchronous Diffusion with dedicated sampling (ablation) | EgoTwin · Nymeria test | HandScore: 0.73 -> 0.81 | Improved |
| add Asynchronous Diffusion with dedicated sampling (ablation) | EgoTwin · Nymeria test | RotErr: 0.62 -> 0.46 | Improved |
| add Asynchronous Diffusion with dedicated sampling (ablation) | EgoTwin · Nymeria test | I-FID: 109.73 -> 98.17 | Improved |
Closest papers by meaning
- UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation (ICCV 2025 · similarity 0.90)
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation (NeurIPS 2025 · similarity 0.89)
- EgoGen: An Egocentric Synthetic Data Generator (CVPR 2024 · similarity 0.89)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.88)
- Exocentric-to-Egocentric Video Generation (NeurIPS 2024 · similarity 0.88)
- PlayerOne: Egocentric World Simulator (NeurIPS 2025 · similarity 0.87)
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.
