UE5-Forest: A Photorealistic Synthetic Stereo Dataset for UAV Forestry Depth Estimation

TL;DR

UE5-Forest is a photorealistic synthetic stereo dataset created in Unreal Engine 5, designed to facilitate UAV forestry depth estimation by providing high-quality disparity maps in complex canopy environments.

Contribution

The paper introduces a novel, photorealistic synthetic stereo dataset for forestry, addressing the lack of ground-truth disparity data in complex natural environments.

Findings

The dataset contains 5,520 stereo pairs with pixel-perfect disparity labels.

Photorealistic quality and geometric plausibility are confirmed through qualitative comparison.

The dataset is publicly available for benchmarking and training stereo-based forestry depth estimation models.

Abstract

Dense ground-truth disparity maps are practically unobtainable in forestry environments, where thin overlapping branches and complex canopy geometry defeat conventional depth sensors -- a critical bottleneck for training supervised stereo matching networks for autonomous UAV-based pruning. We present UE5-Forest, a photorealistic synthetic stereo dataset built entirely in Unreal Engine 5 (UE5). One hundred and fifteen photogrammetry-scanned trees from the Quixel Megascans library are placed in virtual scenes and captured by a simulated stereo rig whose intrinsics -- 63 mm baseline, 2.8 mm focal length, 3.84 mm sensor width -- replicate the ZED Mini camera mounted on our drone. Orbiting each tree at up to 2 m across three elevation bands (horizontal, +45 degrees, -45 degrees) yields 5,520 rectified 1920 x 1080 stereo pairs with pixel-perfect disparity labels. We provide a statistical characterisation of the dataset -- covering disparity distributions, scene diversity, and visual fidelity -- and a qualitative comparison with real-world Canterbury Tree Branches imagery that confirms the photorealistic quality and geometric plausibility of the rendered data. The dataset will be publicly released to provide the community with a ready-to-use benchmark and training resource for stereo-based forestry depth estimation.