Research map / 3D vision / Face and shape
Monocular Mesh Recovery and Body Measurement of Female Saanen Goats
Bo Jin, , ShichaoZhao, Jin Lyu, Bin Zhang, Tao Yu, Liang An, Yebin Liu, Meili Wang
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 |
|---|---|---|---|
| use SaanenGoat parametric model instead of SMAL for scan registration | parametric model fitting · In-Shape test set | mean Chamfer distance (mm): 36.72 -> 10.65 | Improved |
| use SaanenGoat instead of SMAL+ for scan registration | parametric model fitting · In-Shape test set | mean mesh-to-scan distance (mm): 25.14 -> 7.02 | Improved |
| use SaanenGoat instead of SMAL for unseen goats | parametric model fitting · Out-Shape test set | mean Chamfer distance (mm): 39.68 -> 15.30 | Improved |
| use SaanenGoat instead of SMAL+ for unseen goats | parametric model fitting · Out-Shape test set | mean mesh-to-scan distance (mm): 26.32 -> 11.29 | Improved |
| expand SMAL to SMAL+ multi-species shape space | SMAL baseline · In-Shape test set | mean Chamfer distance (mm): 36.72 -> 31.18 | Improved |
| use SaanenGoat in SMALify with depth and normal constraints instead of SMAL | monocular mesh recovery · single-view RGBD, 20 goats | mean Chamfer distance (mm): 89.88 -> 26.58 | Improved |
| use SaanenGoat instead of SMAL+ for monocular recovery | monocular mesh recovery · single-view RGBD, 20 goats | mean Chamfer distance (mm): 76.16 -> 26.58 | Improved |
| use SaanenGoat monocular reconstruction instead of SMAL for T-pose body measurement | body measurement · 20 Saanen goats | average MAE (mm): 62.8 -> 20.6 | Improved |
| use SaanenGoat instead of SMAL+ for body measurement | body measurement · 20 Saanen goats | average MAE (mm): 41.0 -> 20.6 | Improved |
| use SaanenGoat fitting instead of SMAL for six body dimensions | body measurement · 20 Saanen goats | MAE: 4.89 -> 1.90 | Improved |
| fit SaanenGoat to point clouds instead of PointStack keypoint segmentation (chest girth) | body measurement · Chest Girth | MAE (mm): 28.5 -> 15.5 | Improved |
| fit SaanenGoat to point clouds instead of PointStack (chest width) | body measurement · Chest Width | MAE (mm): 11.3 -> 14.6 | Hurt |
Closest papers by meaning
- Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape (ICCV 2023 · similarity 0.86)
- Abstract the Layout, Focus the Detail: A Dual-Granularity Representation Framework for Zero-Shot 3D Visual Grounding (ECCV 2026 · similarity 0.86)
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · similarity 0.84)
- Web-Scale Collection of Video Data for 4D Animal Reconstruction (NeurIPS 2025 · similarity 0.84)
- VAREN: Very Accurate and Realistic Equine Network (CVPR 2024 · similarity 0.83)
- BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting (NeurIPS 2026 · similarity 0.82)
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.
