Gully headcut erosion is a major gully development process contributing to soil-related economic and environmental problems. However, the current understanding of gully headcut is severely lacking due to the difficulty of effectively monitoring relevant processes. In this study, three small-scale experimental plots were established on a field slope of the hilly-gully region of the Chinese Loess Plateau. Fifteen scouring experiments were conducted on each of the plots, while terrestrial laser scanning was used to acquire morphological data of gully headcuts. Using the volume calculations algorithm based on multiscale model-to-model cloud comparison (3D-M3C2), the spatiotemporal distribution of gully headcut erosion was derived, while the erosion mass, deposition mass and sediment yield were also quantified. An improved slicing algorithm and a point cloud segmentation algorithm were proposed to extract the sub-processes of gully headcut erosion. Results showed: (i) Gully headcut erosion was dominated by erosion in cave areas (contributed 67.09% of the sediment yield) and supported by erosion in collapse areas (contributed 33.35% of the sediment yield). This indicated that runoff shear was the main driver of gully headcut erosion and mass movement played a secondary role. (ii) From a vertical perspective, gully headcut erosion was a cyclic process in which erosion of cave areas and collapse areas reinforced each other. From a horizontal perspective, runoff tended to erode the area with weak concavity. (iii) The channel areas contributed the least (even negatively) to sediment yield of gully headcut erosion (−0.44%), while it contained the most complex processes, involving erosion and deposition caused by plunging pool formation and filling, as well as deposition resulting from mass movement and subsequent re-erosion processes. The study provided a valuable reference for the monitoring and process understanding of gully headcut erosion.