Research map / 3D vision / Face and shape
Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
Benjamin Biggs, Oliver Boyne, James Charles, Andrew Fitzgibbon, Roberto Cipolla
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 EM updates of the mixture shape prior (ablation) | Ours · StanfordExtra test (ablation, PCK@0.1) | silhouette IoU: 68.7 -> 74.2 | Improved |
| add mixture-of-Gaussians shape prior (ablation) | Ours · StanfordExtra test (ablation, PCK@0.1) | silhouette IoU: 69.0 -> 74.2 | Improved |
| add scale parameters (ablation) | Ours · StanfordExtra test (ablation, PCK@0.1) | silhouette IoU: 68.3 -> 74.2 | Improved |
| add scale parameters (ablation) | Ours · StanfordExtra test (ablation, PCK@0.1) | PCK@0.1 avg: 60.1 -> 63.7 | Improved |
| add EM updates (ablation) | Ours · StanfordExtra test (ablation, PCK@0.1) | PCK@0.1 avg: 63.2 -> 63.7 | Improved |
| add EM updates (ablation) | Ours · StanfordExtra test (ablation, PCK@0.1) | PCK@0.1 ears: 62.6 -> 60.1 | Hurt |
| add mixture prior without EM steps (ablation) | Ours · StanfordExtra test (ablation, PCK@0.1) | PCK@0.1 avg: 63.1 -> 63.7 | No clear effect |
| add scale parameters (ablation) | Ours · StanfordExtra test (PCK-MAX@0.1) | PCK-MAX@0.1 avg: 72.6 -> 75.7 | Improved |
| add EM updates (ablation) | Ours · StanfordExtra test (PCK-MAX@0.1) | PCK-MAX@0.1 avg: 74.6 -> 75.7 | Improved |
| add mixture-of-Gaussians prior (ablation) | Ours · StanfordExtra test (PCK-MAX@0.1) | PCK-MAX@0.1 avg: 74.9 -> 75.7 | Improved |
| add scale parameters to 3D-M | 3D-M · StanfordExtra test | PCK@0.15 avg: 69.7 -> 70.9 | Improved |
| add EM prior to 3D-M with scaling | 3D-M + scaling · StanfordExtra test | PCK@0.15 avg: 70.9 -> 73.4 | Improved |
Closest papers by meaning
- BITE: Beyond Priors for Improved Three-D Dog Pose Estimation (CVPR 2023 · similarity 0.92)
- BARC: Breed-Augmented Regression Using Classification for 3D Dog Reconstruction from Images (IJCV 2023 · similarity 0.92)
- BARC: Learning To Regress 3D Dog Shape From Images by Exploiting Breed Information (CVPR 2022 · similarity 0.91)
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · similarity 0.89)
- Web-Scale Collection of Video Data for 4D Animal Reconstruction (NeurIPS 2025 · similarity 0.86)
- Learning the 3D Fauna of the Web (CVPR 2024 · 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.
