Research map / 3D vision / Human pose estimation
RGBD-Dog: Predicting Canine Pose from RGBD Sensors
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 |
|---|---|---|---|
| Use RGBD pose prediction and H-GPLVM refinement rather than BADJA silhouette fitting | Canine 3D pose estimation · Dog1–Dog5 | PA MPJPE: 0.976 -> 0.471; 0.491 -> 0.402; 0.610 -> 0.392; 0.730 -> 0.417; 0.997 -> 0.746 | Helped |
| Use RGBD pose prediction and H-GPLVM refinement rather than BADJA silhouette fitting | Canine 3D pose estimation · Dog1–Dog5 | PA PCK 3D: 0.665 -> 0.936; 0.956 -> 1.000; 0.866 -> 0.985; 0.787 -> 0.981; 0.692 -> 0.790 | Helped |
| Add H-GPLVM refinement to the CNN prediction | RGBD-Dog · Dog6, real Kinect | PA MPJPE: 0.866 -> 0.667 | Helped |
| Add H-GPLVM refinement to the CNN prediction | RGBD-Dog · Dog6, real Kinect | PA PCK 3D: 0.745 -> 0.873 | Helped |
| Add H-GPLVM refinement to the CNN prediction | RGBD-Dog · Dog7, real Kinect | PA MPJPE: 0.563 -> 0.557 | Helped |
| Add H-GPLVM refinement to the CNN prediction | RGBD-Dog · Dog7, real Kinect | PA PCK 3D: 0.907 -> 0.922 | Helped |
| Use known dog shape instead of estimating unknown shape | H-GPLVM refinement · Dog6, real Kinect | PA MPJPE: 0.667 -> 0.384 | Helped |
| Use known dog shape instead of estimating unknown shape | H-GPLVM refinement · Dog6, real Kinect | PA PCK 3D: 0.873 -> 0.967 | Helped |
| Allow shape to change on each frame instead of keeping sequence shape constant (ablation) | RGBD-Dog shape fitting · Dog6 | PA MPJPE: 0.667 -> 0.727 | Hurt |
| Allow shape to change on each frame instead of keeping sequence shape constant (ablation) | RGBD-Dog shape fitting · Dog6 | PA PCK 3D: 0.873 -> 0.804 | Hurt |
| Allow shape to change on each frame instead of keeping sequence shape constant (ablation) | RGBD-Dog shape fitting · Dog7 | PA MPJPE: 0.557 -> 0.902 | Hurt |
| Allow shape to change on each frame instead of keeping sequence shape constant (ablation) | RGBD-Dog shape fitting · Dog7 | PA PCK 3D: 0.922 -> 0.706 | Hurt |
Closest papers by meaning
- BITE: Beyond Priors for Improved Three-D Dog Pose Estimation (CVPR 2023 · similarity 0.91)
- Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance (NeurIPS 2025 · similarity 0.86)
- RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos (CVPR 2024 · similarity 0.86)
- BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting (NeurIPS 2026 · similarity 0.86)
- Web-Scale Collection of Video Data for 4D Animal Reconstruction (NeurIPS 2025 · similarity 0.86)
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · 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.