Research map / 3D vision / Face and shape
Birds of a Feather: Capturing Avian Shape Models From Images
Yufu Wang, Nikos Kolotouros, Kostas Daniilidis, Marc Badger
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 |
|---|---|---|---|
| Learn a species-specific shape model instead of using the generic ABM template | ABM bird fitting · CUB test, all 17 species | PCK05: 0.857 -> 0.954 | Improved |
| Learn a species-specific shape model instead of using the generic ABM template | ABM bird fitting · CUB test, all 17 species | IoU: 0.765 -> 0.805 | Improved |
| Use the multi-species AVES model instead of the generic ABM template | Bird shape fitting · CUB held-out species, all 17 species | PCK05: 0.857 -> 0.963 | Improved |
| Use the multi-species AVES model instead of the generic ABM template | Bird shape fitting · CUB held-out species, all 17 species | IoU: 0.756 -> 0.804 | Improved |
| Allow AVES shape coefficients to vary during fitting | Cowbird reconstruction · Penn Aviary | PCK05: 0.406 -> 0.432 | Improved |
| Allow AVES shape coefficients to vary during fitting | Cowbird reconstruction · Penn Aviary | IoU: 0.605 -> 0.606 | No clear effect |
| Add silhouette supervision to the AVES fitting evaluation | Cowbird reconstruction · Penn Aviary, with silhouette | PCK05: 0.412 -> 0.429 | Improved |
| Add silhouette supervision to the AVES fitting evaluation | Cowbird reconstruction · Penn Aviary, with silhouette | IoU: 0.631 -> 0.632 | No clear effect |
| Regress AVES parameters instead of ABM parameters | Single-image 3D bird regression · CUB | PCK05: 0.679 -> 0.703 | Improved |
| Regress AVES parameters instead of ABM parameters | Single-image 3D bird regression · CUB | IoU: 0.706 -> 0.720 | Improved |
| Use AVES shape PCs rather than ResNet50 image features | Phylogeny correspondence analysis · Bird species phylogeny | Pagel's lambda: 0.18 ± 0.20 -> 0.99 ± 0.02 | Improved |
| Add a soft orthogonality constraint and constant basis-vector magnitude (ablation) | Species-specific shape basis learning · Shape reconstruction | reconstruction results | No clear effect |
Closest papers by meaning
- 3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View (ECCV 2020 · similarity 0.91)
- Learning the 3D Fauna of the Web (CVPR 2024 · similarity 0.89)
- RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs (CVPR 2026 · similarity 0.86)
- Reconstructing Animals and the Wild (CVPR 2025 · similarity 0.85)
- BirdCollect: A Comprehensive Benchmark for Analyzing Dense Bird Flock Attributes (AAAI 2024 · similarity 0.85)
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild (NeurIPS 2026 · similarity 0.84)
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.
