Learning-based Monocular 3D Reconstruction of Birds: A Contemporary Survey

TL;DR

This survey reviews recent advances in monocular 3D reconstruction of birds, highlighting methods that estimate pose and shape from 2D images, and discusses their implications for biology and computer vision.

Contribution

It provides the first comprehensive overview of monocular 3D bird reconstruction techniques, comparing their approaches and characteristics.

Findings

Summarizes recent methods in 3D bird reconstruction from monocular images.

Highlights the challenges and solutions in pose and shape estimation.

Bridges insights between computer vision and biological research.

Abstract

In nature, the collective behavior of animals, such as flying birds is dominated by the interactions between individuals of the same species. However, the study of such behavior among the bird species is a complex process that humans cannot perform using conventional visual observational techniques such as focal sampling in nature. For social animals such as birds, the mechanism of group formation can help ecologists understand the relationship between social cues and their visual characteristics over time (e.g., pose and shape). But, recovering the varying pose and shapes of flying birds is a highly challenging problem. A widely-adopted solution to tackle this bottleneck is to extract the pose and shape information from 2D image to 3D correspondence. Recent advances in 3D vision have led to a number of impressive works on the 3D shape and pose estimation, each with different pros and cons. To the best of our knowledge, this work is the first attempt to provide an overview of recent advances in 3D bird reconstruction based on monocular vision, give both computer vision and biology researchers an overview of existing approaches, and compare their characteristics.