Objective The reliability and validity of the SGGC-Net-based motion capture system (SGGC-Net system) and SIMI system for parsing walking gait were compared using a three-dimensional (3D) motion capture system (Vicon) with marker points as a reference standard. Methods Thirty healthy college students were recruited, and their gait characteristics while walking on a treadmill were analyzed. Kinematic data were collected using the Vicon system, and video data were collected synchronously using four cameras to obtain the right shoulder, elbow, hip, knee, and ankle joint angles. Reliability was assessed using intraclass correlation coefficients (ICCs) with 95% confidence intervals and standard error of measurement (SEM). Validity was assessed using multiple correlation coefficients (MCCs) and root mean square errors (RMSEs). Results The ICCs of the maximum and minimum 3D coordinate angles of the upper and lower limb joints of the SGGC-Net system ranged from 0.798－0.990 with an SEM of 0.04°－0.95°, and the ICCs of the SIMI system ranged from 0.650－0.967, with an SEM of 0.31°－1.24°. The ICCs of the SGGC-Net system were higher than those of the SIMI system for all joint angles except for the minimum hip and maximum knee angles. Compared to the joint angle curves derived from the SIMI system, the MCCs of the curves derived from the SGGC-Net system ranged from 0.945－0.996, with RMSEs of 1.44°－4.65°, and the multiple correlation coefficients of the SIMI system ranged from 0.815－0.986, with RMSEs of 2.56° － 9.99°. The MCCs of the SGGC-Net system were greater than those of the SIMI system at all angles except for the ankle joint. The RMSEs of the SGGC-Net system were smaller than those of the SIMI system at all angles except for the ankle joints. Conclusions The SGGC-Net system has better reliability and validity than the SIMI system in most of the variables, and it has better repeatability and accuracy in analyzing walking gait. It can be applied to motion capture environments without marker points, such as technical analysis of athletes’ movements and clinical gait analysis of special populations.