3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View
This addresses the challenge of automated animal pose capture for neuroscience and social behavior studies, particularly for occluded social animals, though it appears incremental as it builds on existing pose estimation methods.
The researchers tackled the problem of robustly estimating pose and shape for social animals like birds, which are often occluded, by introducing a multi-view optimization approach to capture bird shape/pose space and a pipeline for recovering accurate avian postures from single views. They also provided the Penn Aviary Dataset with multi-view annotations from 15 social birds.
Automated capture of animal pose is transforming how we study neuroscience and social behavior. Movements carry important social cues, but current methods are not able to robustly estimate pose and shape of animals, particularly for social animals such as birds, which are often occluded by each other and objects in the environment. To address this problem, we first introduce a model and multi-view optimization approach, which we use to capture the unique shape and pose space displayed by live birds. We then introduce a pipeline and experiments for keypoint, mask, pose, and shape regression that recovers accurate avian postures from single views. Finally, we provide extensive multi-view keypoint and mask annotations collected from a group of 15 social birds housed together in an outdoor aviary. The project website with videos, results, code, mesh model, and the Penn Aviary Dataset can be found at https://marcbadger.github.io/avian-mesh.