This study evaluated the use of telerehabilitation during the postoperative period for patients who underwent total knee arthroplasty (TKA) or unicompartmental knee arthroplasty (UKA). Specifically, this study evaluated the following: (1) patient compliance and adherence to the program, (2) time spent performing physical therapy exercises, (3) the usability of the virtual rehabilitation platform, and (4) clinical outcome scores in a selected primary knee arthroplasty cohort. A total of 157 consecutive patients underwent TKA ( = 18) or UKA ( = 139). These patients used a telerehabilitation system with an instructional avatar, three-dimensional motion measurement and analysis software, and real-time televisit capability designed for arthroplasty patients. Compliance was determined by how many times the patients followed prescribed repetitions of exercises. The total time spent performing exercises for each patient was collected. The usability of the virtual rehabilitation platform (on the patient's end) was evaluated using the system usability scale (SUS) questionnaire. The number of in-person and televisits was recorded for each patient. Patient-reported outcomes were collected through the patient and clinician interfaces and included the Knee Society Score (KSS) for pain and functions, the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) score, and Boston University Activity Measure for Post-Acute Care (AM-PAC) score. Patients spent an average of 29.5 days partaking in the therapy. TKA and UKA patients had a mean of 3.5 and 3.2 outpatient follow-up visits, each, for in-office therapy with a physical therapist, respectively. This figure exceeded the mean number of real-time virtual patient-clinician visits by 0.8 visits per patient in the TKA cohort and by 1 visit per patient in the UKA cohort. Patients spent on average 26.5 minutes per day conducting an average of 13.5 exercises. By the end of rehabilitation, patients had spent an average of 10.8 hours performing exercises, and of all the exercises performed, approximately 21 exercises were uniquely designed. Mean SUS score in the cohort was 93 points, which was interpreted as being above the 50th percentile point of the scale. Following therapy, KSS pain and function scores improved markedly and the improvements were measured at 368% for TKA and 350% for UKA (pain) and 27% for UKA and 33% for TKA (function). In addition, WOMAC scores improved by 57% and 66% for UKA and TKA patients while the improvement in AM-PAC scores was at 22% and 24%. This telerehabilitation platform encouraged clinician-patient interaction beyond the hospital setting and offers the advantage of cost savings, convenience, at-home monitoring, and coordination of care, all of which are geared to improve adherence and overall patient satisfaction. Additionally, the biometric data can be used to develop custom physical therapy regimens to assure proper rehabilitation, which is lacking in other telerehabilitation applications that use noninteractive videos that can be watch...