Research map / 3D vision / Human pose estimation
Reconstructing Signing Avatars From Video Using Linguistic Priors
Maria-Paola Forte, Peter Kulits, Chun-Hao P. Huang, Vasileios Choutas, Dimitrios Tzionas, Katherine J. Kuchenbecker, Michael J. Black
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 linguistic symmetry and hand-pose invariance constraints | SMPLify-SL · DGS mocap dataset | TR-V2V error (mm), upper body and hands: 56.07 -> 55.63 upper body; 22.23 -> 19.22 left hand; 18.83 -> 17.50 right hand | Improved |
| Add hand-pose symmetry constraint (ablation) | SMPLify-SL · Symmetric signs | TR-V2V error (mm), both hands: 19.54 -> 18.41 | Improved |
| Add hand-pose invariance constraint (ablation) | SMPLify-SL · Symmetric signs | TR-V2V error (mm), both hands: 19.54 -> 18.46 | Improved |
| Add both symmetry and hand-pose invariance constraints (ablation) | SMPLify-SL · Symmetric signs | TR-V2V error (mm), both hands: 19.54 -> 17.50 | Improved |
| Add symmetry constraint alongside hand-pose invariance (ablation) | SMPLify-SL · Symmetric signs | TR-V2V error (mm), right hand: 17.16 -> 17.29 | Hurt |
| Add hand-pose invariance constraint (ablation) | SMPLify-SL · Asymmetric signs | TR-V2V error (mm), both hands: 20.50 -> 18.60 | Improved |
| Use Signify rather than SMPLify-SL | SMPLify-SL · ASL Handshape Dictionary perceptual study | sign recognition accuracy: 74.8% -> 86.2% | Improved |
| Use Signify rather than PyMAF-X | PyMAF-X · ASL Handshape Dictionary perceptual study | sign recognition accuracy: 62.0% -> 86.2% | Improved |
| Replace real-person video with Signify reconstruction | Real-person video · ASL Handshape Dictionary perceptual study | sign recognition accuracy: 90.9% -> 86.2% | No clear effect |
| Add a black long-sleeved t-shirt or use a fully textured avatar (ablation) | Signify avatar · Second ASL perceptual study | sign recognition and naturalness | No clear effect |
Closest papers by meaning
- SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark (ECCV 2024 · similarity 0.91)
- SignRefine: Adapting Foundational Video Models for Sign Language Generation (ECCV 2026 · similarity 0.89)
- PHOSA: Photorealistic 3D Sign Avatar Modeling and Benchmark (ECCV 2026 · similarity 0.89)
- Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text (CVPR 2024 · similarity 0.88)
- Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production (AAAI 2025 · similarity 0.87)
- Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment (NeurIPS 2026 · 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.
