Research map / 3D vision / 3D generation
Flow Guided Transformable Bottleneck Networks for Motion Retargeting
Check 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 |
|---|---|---|---|
| add multi-resolution bottlenecks (ablation) | Flow Guided Transformable Bottleneck Networks · iPER (foreground) | SSIM: 0.870 -> 0.878 | Helped |
| add multi-resolution bottlenecks (ablation) | Flow Guided Transformable Bottleneck Networks · iPER (foreground) | LPIPS: 0.051 -> 0.045 | Helped |
| add flow-warped skip connections (ablation) | Flow Guided Transformable Bottleneck Networks · iPER (foreground) | SSIM: 0.856 -> 0.878 | Helped |
| add flow-warped skip connections (ablation) | Flow Guided Transformable Bottleneck Networks · iPER (foreground) | LPIPS: 0.059 -> 0.045 | Helped |
| add unsupervised random-rotation supervision (ablation) | Flow Guided Transformable Bottleneck Networks · iPER (foreground) | SSIM: 0.876 -> 0.878 | Helped |
| add unsupervised random-rotation supervision (ablation) | Flow Guided Transformable Bottleneck Networks · iPER (foreground) | LPIPS: 0.047 -> 0.045 | Helped |
| increase the number of target reference images from one to four (ablation) | Flow Guided Transformable Bottleneck Networks · iPER | SSIM: 0.878 -> 0.882 | Helped |
| increase the number of target reference images from one to four (ablation) | Flow Guided Transformable Bottleneck Networks · iPER | LPIPS: 0.045 -> 0.043 | Helped |
Closest papers by meaning
- H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning (NeurIPS 2026 · similarity 0.88)
- DisPose: Disentangling Pose Guidance for Controllable Human Image Animation (ICLR 2025 · similarity 0.87)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.87)
- VideoMDM: Towards 3D Human Motion Generation From 2D Supervision (NeurIPS 2026 · similarity 0.86)
- DisMo: Disentangled Motion Representations for Open-World Motion Transfer (NeurIPS 2025 · similarity 0.86)
- Scaling Large Motion Models with Million-Level Human Motions (ICML 2025 · 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.