Generalization Evaluation of Deep Stereo Matching Methods for UAV-Based Forestry Applications

TL;DR

This study systematically evaluates eight state-of-the-art stereo matching methods for UAV-based forestry, revealing scene-dependent performance patterns and identifying DEFOM as a robust baseline for vegetation depth estimation.

Contribution

First zero-shot evaluation of stereo methods on forestry environments, highlighting cross-domain robustness and scene-specific strengths of foundation versus iterative models.

Findings

Foundation models excel on structured scenes with low error rates.

Iterative methods maintain robustness across diverse domains.

RAFT-Stereo fails catastrophically on ETH3D due to negative disparity predictions.

Abstract

Autonomous UAV forestry operations require robust depth estimation methods with strong cross-domain generalization. However, existing evaluations focus on urban and indoor scenarios, leaving a critical gap for specialized vegetation-dense environments. We present the first systematic zero-shot evaluation of eight state-of-the-art stereo methods--RAFT-Stereo, IGEV, IGEV++, BridgeDepth, StereoAnywhere, DEFOM (plus baseline methods ACVNet, PSMNet, TCstereo)--spanning iterative refinement, foundation model, and zero-shot adaptation paradigms. All methods are trained exclusively on Scene Flow and evaluated without fine-tuning on four standard benchmarks (ETH3D, KITTI 2012/2015, Middlebury) plus a novel 5,313-pair Canterbury forestry dataset captured with ZED Mini camera (1920x1080). Performance reveals scene-dependent patterns: foundation models excel on structured scenes (BridgeDepth: 0.23 px on ETH3D, 0.83-1.07 px on KITTI; DEFOM: 0.35-4.65 px across benchmarks), while iterative methods maintain cross-domain robustness (IGEV++: 0.36-6.77 px; IGEV: 0.33-21.91 px). Critical finding: RAFT-Stereo exhibits catastrophic ETH3D failure (26.23 px EPE, 98 percent error rate) due to negative disparity predictions, while performing normally on KITTI (0.90-1.11 px). Qualitative evaluation on Canterbury forestry dataset identifies DEFOM as the optimal gold-standard baseline for vegetation depth estimation, exhibiting superior depth smoothness, occlusion handling, and cross-domain consistency compared to IGEV++, despite IGEV++'s finer detail preservation.