WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation

TL;DR

WildDepth introduces a multimodal dataset with synchronized RGB and LiDAR data for 3D perception tasks on diverse animals, improving depth and reconstruction accuracy.

Contribution

The paper presents WildDepth, a novel multimodal dataset and benchmark suite for animal depth estimation and 3D reconstruction across various environments.

Findings

Multi-modal data improves depth estimation accuracy by up to 10% RMSE.

RGB-LiDAR fusion enhances 3D reconstruction fidelity by 12%.

WildDepth enables cross-domain generalization for animal perception.

Abstract

Depth estimation and 3D reconstruction have been extensively studied as core topics in computer vision. Starting from rigid objects with relatively simple geometric shapes, such as vehicles, the research has expanded to address general objects, including challenging deformable objects, such as humans and animals. However, for the animal, in particular, the majority of existing models are trained based on datasets without metric scale, which can help validate image-only models. To address this limitation, we present WildDepth, a multimodal dataset and benchmark suite for depth estimation, behavior detection, and 3D reconstruction from diverse categories of animals ranging from domestic to wild environments with synchronized RGB and LiDAR. Experimental results show that the use of multi-modal data improves depth reliability by up to 10% RMSE, while RGB-LiDAR fusion enhances 3D reconstruction fidelity by 12% in Chamfer distance. By releasing WildDepth and its benchmarks, we aim to foster robust multimodal perception systems that generalize across domains.