Adding Another Dimension to Image-based Animal Detection

arXiv:2604.09210v1 Announce Type: new Abstract: Monocular imaging of animals inherently reduces 3D structures to 2D projections. Detection algorithms lead to 2D bounding boxes that lack information about animal's orientation relative to the camera. To build 3D detection methods for RGB animal images, there is a lack of labeled datasets; such labeling processes require 3D input streams along with RGB data. We present a pipeline that utilises Skinned Multi Animal Linear models to estimate 3D bounding boxes and to project them as robust labels into 2D image space using a dedicated camera pose refinement algorithm. To assess which sides of the animal are captured, cuboid face visibility metrics are computed. These 3D bounding boxes and metrics form a crucial step toward developing and benchmarking future monocular 3D animal detection algorithms. We evaluate our method on the Animal3D dataset, demonstrating accurate performance across species and settings.

Related

• E-3DPSM: A State Machine for Event-Based Egocentric 3D Human Pose Estimation
• WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects
• MASS: Mesh-inellipse Aligned Deformable Surfel Splatting for Hand Reconstruction and Rendering from Egocentric Monocular Video
• Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion
• MVOS_HSI: A Python Library for Preprocessing Agricultural Crop Hyperspectral Data

Source: arXiv cs.CV | 2026-04-13