Research map / 3D vision / Human pose estimation
MoCaNet: Motion Retargeting In-the-Wild via Canonicalization Networks
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 |
|---|---|---|---|
| Train on Solo-Dancer in-the-wild data rather than the synthetic training setup | MoCaNet · Mixamo testset overall | MSE ×10^-2: 0.891 -> 0.878 | Helped |
| Train on Solo-Dancer in-the-wild data rather than the synthetic training setup | MoCaNet · Mixamo testset overall | MPJPE ×10^-1: 1.261 -> 1.253 | Helped |
| Use dual-canonicalized skeleton sequences instead of TransMoMo motion embeddings | Mixamo motion clustering · Mixamo motion clustering | ARI: 0.241 -> 0.347 | Helped |
| Use dual-canonicalized skeleton sequences instead of TransMoMo motion embeddings | Mixamo motion clustering · Mixamo motion clustering | AMI: 0.620 -> 0.707 | Helped |
| Add adversarial loss (ablation) | MoCaNet · Mixamo testset | MSE ×10^-2: 1.579 -> 0.891 | Helped |
| Add view canonicalization loss (ablation) | MoCaNet · Mixamo testset | MSE ×10^-2: 1.240 -> 0.891 | Helped |
| Add structure canonicalization loss (ablation) | MoCaNet · Mixamo testset | MSE ×10^-2: 1.599 -> 0.891 | Helped |
| Add adversarial loss (ablation) | MoCaNet · Mixamo testset | MPJPE ×10^-1: 1.785 -> 1.261 | Helped |
| Add view canonicalization loss (ablation) | MoCaNet · Mixamo testset | MPJPE ×10^-1: 1.602 -> 1.261 | Helped |
| Add structure canonicalization loss (ablation) | MoCaNet · Mixamo testset | MPJPE ×10^-1: 1.693 -> 1.261 | Helped |
| Apply 3D loss terms and dynamic view to TransMoMo (ablation) | TransMoMo · Mixamo testset | MSE ×10^-2: 1.652 -> 1.688 | Mixed |
Closest papers by meaning
- Semantics-aware Motion Retargeting with Vision-Language Models (CVPR 2024 · similarity 0.88)
- VideoMDM: Towards 3D Human Motion Generation From 2D Supervision (NeurIPS 2026 · similarity 0.86)
- Emergence of a Shared Canonical Object Frame from In-the-Wild Videos (NeurIPS 2026 · similarity 0.86)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.86)
- DisMo: Disentangled Motion Representations for Open-World Motion Transfer (NeurIPS 2025 · similarity 0.85)
- HumanMM: Global Human Motion Recovery from Multi-shot Videos (CVPR 2025 · similarity 0.85)
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.