Rendering acceleration based on JND-guided sampling prediction

When using Monte Carlo Path Tracing (MCPT) method to render 3D scenes, artifacts may occur due to insufficient sampling, and directly increasing the number of samples can increase the time cost of the rendering algorithm. An effective strategy is to adaptively allocate the number of samples per pixel in an iterative manner. However, iterative operations introduce additional computational overhead during the rendering process. To solve this problem, we proposed a rendering acceleration method that does not require iterative computation. This method combines the Just Noticeable Difference (JND) information and uses a neural network to predict the sampling matrix of the scene, which is adjusted based on the lighting information in the pre-rendered image. First, we extract the JND information of pre-rendered images during the preprocessing and estimate the fast convergence regions in the scene (such as environment map regions, light source regions, etc.). Then, we use Conv-LSTM to estimate the JND features of high-quality rendered images. We design a multi-feature fusion network to predict the number of samples required for each pixel during the rendering process. The network takes the preprocessed pre-rendered images as the input of the encoder, which are fused with the output of Conv-LSTM as the input of the decoder to output the corresponding sampling matrix. In addition, we noticed that areas with darker lighting are more difficult to converge during the rendering process. Therefore, we calculated the lighting clustering results of the pre-rendered image and adjusted the sampling matrix output by the sampling prediction model based on the lighting clustering results. The experimental results indicate that our method has better performance compared to the current methods.