Research map / 3D vision / Face and shape
BARC: Learning To Regress 3D Dog Shape From Images by Exploiting Breed Information
Nadine Rüegg, Silvia Zuffi, Konrad Schindler, Michael J. Black
Check 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 breed triplet and classification losses (ablation) | BARC · Breed prototype consistency (20 breeds) | Error [m]: 0.0858 -> 0.0776 | Improved |
| add the breed-specific 3D model loss (ablation) | BARC with breed similarity · Breed prototype consistency (20 breeds) | Error [m]: 0.0776 -> 0.0695 | Improved |
| add breed triplet and classification losses (ablation) | BARC without breed losses · AMT perceptual preference | Percentage preferring method: 62.55% : 37.45% | Improved |
| add the breed-specific 3D model loss (ablation) | BARC with breed similarity · AMT perceptual preference | Percentage preferring method: 60.36% : 39.64% | Improved |
| add breed classification loss without triplet or 3D losses (ablation) | BARC · Breed prototype consistency | Error [m]: 0.0858 -> 0.0799 | Improved |
| add triplet loss to breed classification (ablation) | BARC with breed classification · Breed prototype consistency | Error [m]: 0.0799 -> 0.0776 | Improved |
| increase triplet loss weight from 5 to 10 (ablation) | BARC with breed classification · Breed prototype consistency | Error [m]: 0.0776 -> 0.0776 | No clear effect |
| add breed similarity and breed-specific 3D supervision | BARC · AMT perceptual preference against WLDO | Percentage preferring method: 92.41% : 7.59% | Improved |
| add breed similarity and breed-specific 3D supervision | BARC · StanExt test | PCK @ 0.15 Avg: BARC: 82.8; WLDO: 78.8 | Mixed |
Later papers that compared with this method
2 later accepted papers report BARC as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos (ECCV 2024 · better on 3 of 3 shared results)
- BITE: Beyond Priors for Improved Three-D Dog Pose Estimation (CVPR 2023 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BARC: Breed-Augmented Regression Using Classification for 3D Dog Reconstruction from Images (IJCV 2023 · similarity 0.98)
- Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop (ECCV 2020 · similarity 0.91)
- BITE: Beyond Priors for Improved Three-D Dog Pose Estimation (CVPR 2023 · similarity 0.90)
- Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape (ICCV 2023 · similarity 0.89)
- Learning the 3D Fauna of the Web (CVPR 2024 · similarity 0.87)
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · similarity 0.87)
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.
