Research map / 3D vision / Human pose estimation
A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos
Thiago L. Gomes, Renato Martins, João Ferreira, Rafael Azevedo, Guilherme Campelo Fortunato Torres, Erickson R. Nascimento
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 2D/3D motion constraints (ablation) | retargeting method · dataset, all motion types | MSE: 285.33 -> 259.75 | Improved |
| add motion regularization (ablation) | retargeting method · dataset, all motion types | FVD: 887.94 -> 738.96 | Improved |
| add semantic-guided deformation (ablation) | retargeting method · dataset, all motion types | FVD: 879.86 -> 738.96 | Improved |
| add visibility mask (ablation) | retargeting method · dataset, all motion types | FVD: 789.06 -> 738.96 | Improved |
| add visibility mask (ablation) | retargeting method · dataset, all motion types | MSE: 273.45 -> 259.75 | Improved |
| add motion retargeting with constraints instead of direct transfer (ablation) | retargeting · end-effector error | pixels error: 20.80 -> 3.90 | Improved |
| add semantic guidance and visibility maps (ablation) | forgery detection · shake hands | forgery score: 34.91 -> 5.67 | Improved |
| use Ours instead of Vid2Vid | retargeting · dataset avg | MSE: 303.32 -> 274.11 | Improved |
| use Ours instead of EBDN | retargeting · dataset avg | FVD: 768.37 -> 738.96 | Improved |
| use Ours instead of Vid2Vid | retargeting · dataset avg | SSIM: 0.862 -> 0.864 | No clear effect |
| use Ours instead of iPER | retargeting · iPER dataset | SSIM: 0.8410 -> 0.8936 | Improved |
| use Ours instead of iPER | retargeting · iPER dataset | FVD: 955 -> 1269 | Hurt |
Closest papers by meaning
- Flow Guided Transformable Bottleneck Networks for Motion Retargeting (CVPR 2021 · similarity 0.90)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.88)
- Semantics-aware Motion Retargeting with Vision-Language Models (CVPR 2024 · similarity 0.87)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.86)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.86)
- ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters (AAAI 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.
