Research map / 3D vision / Human pose estimation
Motion Representations for Articulated Animation
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 |
|---|---|---|---|
| replace regression-based motion estimation with PCA-based region motion estimation (ablation) | Motion Representations for Articulated Animation · TaiChiHD (256) | AKD: 9.58 -> 5.59 | Helped |
| replace regression-based motion estimation with PCA-based region motion estimation (ablation) | Motion Representations for Articulated Animation · TaiChiHD (256) | L1 error: 0.056 -> 0.048 | Helped |
| add an affine background motion model (ablation) | Motion Representations for Articulated Animation · TaiChiHD (256) | L1 error: 0.059 -> 0.048 | Helped |
| add an affine background motion model (ablation) | Motion Representations for Articulated Animation · TaiChiHD (256) | AKD: 5.55 -> 5.59 | No clear effect |
| use the proposed method instead of FOMM | unsupervised animation · TaiChiHD (256) | AKD: 6.53 -> 5.58 | Helped |
| use the proposed method instead of FOMM | unsupervised animation · TaiChiHD (512) | AKD: 17.12 -> 13.86 | Helped |
| use the proposed method instead of FOMM | unsupervised animation · TED-talks | AKD: 7.07 -> 3.75 | Helped |
| use the proposed method instead of FOMM | unsupervised animation · VoxCeleb | AKD: 1.27 -> 1.28 | No clear effect |
| use animation via disentanglement instead of standard animation | Motion Representations for Articulated Animation · TED-talks | user preference: 65.6% | Helped |
| use the proposed method instead of FOMM | unsupervised animation · TED-talks | user preference: 96.6% | Helped |
Closest papers by meaning
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.89)
- Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video (NeurIPS 2026 · similarity 0.89)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.88)
- Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis (NeurIPS 2024 · similarity 0.88)
- Continuous Piecewise-Affine Based Motion Model for Image Animation (AAAI 2024 · similarity 0.87)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 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.