Participating media are ubiquitous in nature and are also major elements in many rendering applications such as special effects, digital games, and simulation systems. Physically-based simulation and reproduction of their appearance can significantly boost the realism and immersion of 3D virtual scenes. However, both the underlying structures of participating media and the light propagation in them are very complex. Therefore, rendering with participating media is a difficult task and hot topic in computer graphics so far. In order to facilitate the treatment in rendering and lower the computational cost, classical methods for participating media rendering are always based on two assumptions: independent scattering and local continuity. These two assumptions are also the building blocks of classical radiative transfer equation (RTE). However, most participating media in nature do not satisfy these two assumptions. This results in the noticeable discrepancy between rendered images and real images. In recent years, these two assumptions have been relaxed by incorporating more physically accurate methods to model participating media, thus significantly improving the physical realism of participating media rendering. This survey analyzes and discusses existing non-classical participating media rendering techniques from two aspects: correlated media rendering and discrete media rendering. The differences between classical and non-classical participating media rendering are discussed. The principles, advantages, and limitations behind each method are also described. Finally, some future directions are provided around non-classical participating media rendering that are worth delving into. It is hoped that this survey can inspire researchers to study non-classical participating media rendering by addressing some critical issues. It is also hoped that this survey can be a guidance for engineers from industry to improve their renderers by considering non-classical participating media rendering.