Research map / 3D vision / Human pose estimation
BITE: Beyond Priors for Improved Three-D Dog Pose Estimation
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 |
|---|---|---|---|
| Use BITE instead of BARC | 3D dog reconstruction · Rendered dog scans | scan-to-mesh error (cm): 2.40 -> 2.07 | Helped |
| Use BITE instead of BARC | 3D dog reconstruction · Rendered dog scans | mesh-to-scan error (cm): 3.93 -> 3.15 | Helped |
| Add test-time optimization (ablation) | BITE · Rendered dog scans | mesh-to-scan error (cm): 3.15 -> 2.84 | Helped |
| Add D-SMAL in place of the generic SMAL dog model (ablation) | BARC · Rendered dog scans | scan-to-mesh error (cm): 2.40 -> 2.32 | Helped |
| Add ground-contact losses (ablation) | BARC+ · Rendered dog scans | mesh-to-scan error (cm): 3.92 -> 3.48 | Helped |
| Add ground-contact losses to the refinement network (ablation) | BITE · Rendered dog scans | mesh-to-scan error (cm): 4.16 -> 3.15 | Helped |
| Use the pose-balanced data sampler (ablation) | BITE · Rendered dog scans | scan-to-mesh error (cm): 2.09 -> 2.07 | Helped |
| Keep shape prediction in BARC+ rather than updating shape through refinement (ablation) | BITE · Rendered dog scans | mesh-to-scan error (cm): 3.17 -> 3.15 | Helped |
| Keep shape prediction out of the refinement branch (ablation) | BITE · Rendered dog scans | mesh-to-scan error (cm): 4.24 -> 3.15 | Helped |
Closest papers by meaning
- RGBD-Dog: Predicting Canine Pose from RGBD Sensors (CVPR 2020 · similarity 0.91)
- Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance (NeurIPS 2025 · similarity 0.88)
- BEAST3D: animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting (NeurIPS 2026 · similarity 0.86)
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · similarity 0.86)
- VAREN: Very Accurate and Realistic Equine Network (CVPR 2024 · similarity 0.85)
- SAOR: Single-View Articulated Object Reconstruction (CVPR 2024 · 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.