Plant height (PH) is a helpful parameter for understanding plant development and stress. Therefore, extensive experimental fields can benefit by collecting different plant parameters, including PH, using unoccupied aerial vehicle (UAV) borne sensor data. Principally, three-dimensional (3D) data of the plant canopy requires to derive PH. A plant canopy's 3D point clouds (PCs) can be generated from UAV-borne LiDAR data and UAV-borne high-resolution digital images known as photogrammetric PCs. However, these two methods employ two different techniques, and also their total financial investment is dissimilar. Therefore, this study aims to compare the PC of the plant canopy generated from UAV-borne photogrammetric and LiDAR methods for estimating maize PH. UAV-borne RGB image (DJI Phantom 4 advanced RGB camera) and LiDAR (RIEGL Mini-VUX-1 LiDAR on DJI Matrice 600 pro) data were collected on a silage maize field experimental set-up at Neu-Eichenberg, Hessen, Germany in September 2020. Subsequently, plant-level PH and experimental plot-level PH were collected using a ruler. Later, canopy height matrices (e.g., mean, percentiles) derived from photogrammetric and LiDAR PCs were employed to train and validate linear regression models to estimate plant-level and plot-level maize PHs. The 99th percentile from both Photogrammetric and LiDAR PCs showed the best PH estimation accuracy (cross-validated root mean square error (RMSEcv) = 6 cm and coefficient of determination (R²cv) = 0.87). For the plot level, the 98th percentile of LiDAR PC obtained the highest model performances (RMSEcv = 5 cm; R²cv = 0.87). In contrast, the 90th percentile from the photogrammetric PC showed the lowest plot-level PH estimation error (RMSEcv = 7 cm; R²cv = 0.82). The preliminary results from this study confirmed that the PCs derived from both methods could accurately be related to plant-level maize PH. At the same time, LiDAR PC showed slightly better plot-level maize PH estimation results. However, regarding the financial investment for these two methods, the initial investment for LiDAR data collection (ca. 100 000 €) is comparably higher than the photogrammetric method (ca. 10 000 €). Therefore, this study suggests that the less expensive UAV-borne photogrammetric PC is suitable for accurately estimating maize PH.