Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green

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.

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

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.
Paper Structure (25 sections, 4 equations, 6 figures, 3 tables)

This paper contains 25 sections, 4 equations, 6 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. UAV-Based Depth Estimation in Forestry
  4. Stereo Matching and the Need for Dense Labels
  5. Synthetic Datasets for Depth Estimation
  6. Dataset Construction
  7. Overview
  8. Stereo Geometry and Camera Model
  9. Tree Assets
  10. Drone Camera Simulation
  11. Rendering and Ground-Truth Extraction
  12. Dataset Splits and Statistics
  13. Data Format and Organisation
  14. Dataset Analysis
  15. Disparity Distribution
  16. ...and 10 more sections

Figures (6)

  • Figure 1: Overview of the UE5-Forest dataset generation pipeline.
  • Figure 2: trees in UE5
  • Figure 3: Simulated stereo camera trajectory. Three rings of 16 viewpoints each at $0^{\circ}$ (H), $+45^{\circ}$ (U), and $-45^{\circ}$ (D) elevation.
  • Figure 4: Ground-truth disparity distribution of the UE5-Forest dataset. The range is consistent with the 0.1--2 m operating distance of the simulated drone.
  • Figure 5: Qualitative comparison between UE5-Forest synthetic renders (left) and real-world Canterbury Tree Branches images (right). Camera parameters are matched, producing similar perspective geometry and disparity ranges.
  • ...and 1 more figures