Research map / 3D vision / Human pose estimation
Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| translate the change in the human image onto the robot image (re-rendering) rather than image-to-image translation, vs CycleGAN (ablation) | goal generator · pouring test set | L2: 99.15 -> 39.98 | Helped |
| add GAN loss and re-rendering to L1-only regression for goal generator (ablation) | goal generator · pouring test set | L1: 72.57 -> 52.37 | Helped |
| decoupled hierarchy instead of end-to-end network | third-person imitation on Baxter · real robot pouring | pour success: 8% -> 60% | Helped |
| decoupled hierarchy instead of end-to-end network | third-person imitation on Baxter · real robot placing (trained on pouring only) | drop success: 10% -> 50% | Helped |
| task-agnostic inverse model instead of end-to-end | low-level controller · MIME 5 novel tasks | RMSE: 24.83 -> 16.90 | Helped |
| inverse model vs end-to-end, trained on all tasks | inverse model · pouring novel objects, all-task training | RMSE: 14.7 -> 14.4 | No clear effect |
| inverse model vs end-to-end, single-task training | inverse model · pouring novel objects | RMSE: 8.9 -> 8.1 | Helped |
Closest papers by meaning
- OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation (NeurIPS 2025 · similarity 0.88)
- Imitation Learning from a Single Temporally Misaligned Video (ICML 2025 · similarity 0.87)
- Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models (ICLR 2024 · similarity 0.87)
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations (NeurIPS 2025 · similarity 0.86)
- SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation (ICML 2024 · similarity 0.86)
- Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control (NeurIPS 2024 · 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.