With the widespread advent of digital technologies, traditional perspectives in rock mechanics research are poised for further expansion. This paper presents a Brazilian test conducted on granite after non-steady-state thermal disturbance at 25 °C, 200 °C, 400 °C, and 600 °C, with detailed documentation of the damage process and failure response using an acoustic emission (AE) apparatus and a digital image correlation (DIC) system. Subsequently, utilizing point cloud data captured by a three-dimensional (3D) laser scanning system, a digital reconstruction of the failed specimen’s fracture surface was accomplished. The 3D fractal characteristics and roughness response of the digitized fracture surface were studied using the box-counting method and least squares approach. Furthermore, texture information of the digitized fracture surface was calculated using the Gray Level Co-occurrence Matrix (GLCM), and statistical characteristics describing the elevation distribution were analyzed. The results elucidate the influence of thermal disturbance temperature on the mechanical parameters of the specimen, acoustic emission behavior, surface strain field evolution, and digital fracture morphology characteristics. The findings indicate a non-linear degradation effect of temperature on the specimen’s tensile strength, with a reduction reaching 80.95% at 600 °C, where acoustic emission activity also peaked. The rising thermal disturbance temperature inhibited the crack initiation load at the specimen’s center but expanded the high-strain concentration areas and the growth rate of horizontal displacement. Additionally, varying degrees of linear or non-linear relationships were discovered between thermal disturbance temperature and the 3D fractal dimension of the fracture surface, average roughness (Ra), peak roughness (Rz), and root mean square roughness (Rq), confirming the potential of Rsm in predicting the 3D fractal dimension of Brazilian test fracture surfaces. The study of the GLCM of the digitized 3D fracture surface demonstrated a high dependency of its four second-order statistical measures on thermal disturbance temperature. Finally, the statistical parameters of the fracture surface’s elevation values showed a significant non-linear relationship with thermal disturbance temperature, with a critical temperature point likely existing between 400 and 600 °C that could precipitate a sudden change in the fracture surface’s elevation characteristics.