The aim of this study was to compare clinical and second-look arthroscopic outcomes between bone marrow aspirate concentrate (BMAC) augmentation and human umbilical cord blood-derived mesenchymal stromal cell (hUCB-MSC) implantation in high tibial osteotomy (HTO) for medial compartmental knee osteoarthritis and identify the relationship between articular cartilage regeneration and HTO outcomes. A total of 176 patients who underwent HTO combined with a BMAC or hUCB-MSC procedure for medial compartment osteoarthritis (Kellgren-Lawrence grade 3) between June 2014 and September 2018 with a minimum follow-up of 2years were reviewed. After HTO, multiple holes were drilled at cartilage defect sites of the medial femoral condyle (MFC), and then prepared BMAC or hUCB-MSCs in combination with scaffolds were implanted in the MFC lesions. After propensity score matching based on sex, age, body mass index, and lesion size, 55 patients in each of the BMAC and hUCB-MSC groups were successfully matched. Second-look arthroscopic findings were assessed according to the International Cartilage Repair Society (ICRS) Cartilage Repair Assessment (CRA) grading system and Koshino staging system. Clinical outcomes were evaluated using the International Knee Documentation Committee (IKDC), Knee Injury and Osteoarthritis Outcome Score (KOOS), Short-Form 36 (SF-36), and Tegner activity scores. At a mean follow-up of 33months, clinical outcomes including IKDC, KOOS, SF-36, and Tegner activity scores were significantly improved in both groups (p < 0.001); however, there were no differences between the two groups. Second-look arthroscopy showed better healing of regenerated cartilage in the hUCB-MSC group (Grade I [4 cases, 9.1%]; Grade II [30 cases, 68.2%]; Grade III [11 cases, 22.7%]) than in the BMAC group (Grade I [1 case, 2.7%]; Grade II [20 cases, 54.1%]; Grade III [11 cases, 29.7%]; Grade IV [5 cases, 13.5%]) according to the ICRS CRA grading system (p = 0.040). There was no significant intergroup difference in terms of defect coverage based on the Koshino staging system (p = 0.057). Moreover, ICRS CRA grades at second-look arthroscopy were significantly correlated with clinical outcomes (r = -0.337; p = 0.002). There were no significant differences in the clinical outcomes between the two groups. Both treatments provided similar, reliable outcomes in terms of pain relief, functional scores, and quality of life at a mean follow-up of 33months. However, hUCB-MSC implantation was more effective than BMAC augmentation for articular cartilage regeneration.