Background: Fatty infiltration of the rotator cuff muscles is highly related to poor outcomes after rotator cuff tears. Fat fraction (FF) based on traditional 2–dimensional measurements (2D-FF) from a single sagittal Y-view slice cannot determine intramuscular FF in the rotator cuff muscles; the newly developed 3–dimensional method (3D-FF) is supposed to precede 2D measurements for intramuscular FF evaluation in accuracy and reliability. Purpose: (1) To measure 3D-FF and (2) to compare 3D-FF and 2D-FF in terms of quantitative values and intra- and interobserver agreement. Study Design: Cohort study (diagnosis); Level of evidence, 2. Methods: Six-point Dixon magnetic resonance imaging was performed in patients with full–thickness supraspinatus tears. 2D-FF was calculated on a single sagittal Y-view. Semiautomatic segmentation software (ITK-SNAP) was used to reconstruct 3D volumes of the supraspinatus muscle and fat. 3D-FF was obtained by dividing the fat volume by the total volume of the supraspinatus muscle. A paired t test was used to compare the individual differences between 2D-FF and 3D-FF results. Linear regression and Bland-Altman analyses were performed to determine the agreement between 2D-FF and 3D-FF. Intraclass correlation coefficients (ICCs) were calculated to determine intra- and interobserver agreement. Results: The 3D muscular and fatty models presented an inhomogeneous distribution of intramuscular fat in the supraspinatus, indicating the superiority of 3D-FF over 2D-FF in capturing all muscle morphologic information. 2D-FF was significantly higher than 3D-FF in the supraspinatus with large (19.5% ± 5.9% vs 16.2% ± 3.7%; P = .002) and massive (34.8% ± 13.3% vs 26.2% ± 9.4%; P < .001) rotator cuff tears. 2D-FF overestimated the FF compared with 3D-FF by >50% in 14.7% of all patients and by >15% in 67.6% of patients with large or massive RCTs. The discrepancy between 2D-FF and 3D-FF increased with increasing mean FF. The intra- and interobserver agreement of 3D-FF (ICCs, 0.89-0.99 and 0.89-0.95) was superior to that of 2D-FF (ICCs, 0.71-0.95 and 0.64-0.79). Conclusion: 3D-FF indicated an inhomogeneous distribution of intramuscular fat by capturing all muscle and fat morphologic information. In patients with large and massive rotator cuff tears, 2D-FF of the supraspinatus was significantly higher than 3D-FF. 3D-FF was more reliable than 2D-FF for estimating fatty infiltration in the supraspinatus, with better intra- and interobserver agreement.