Abstract: In order to deal with the problems of the temporal anti-aliasing algorithm, such as ghosting, blurring, flickering, and loss of sub-pixel details when processing multiplexing between frames, in the cases of many high-frequency color regions or fine models in the scene, this paper proposed the temporal anti-aliasing algorithm based on sparse super-sampling. The core idea was that, based on the temporal anti-aliasing algorithm, for pixels that cannot reuse historical frames, super-sampling in the spatial domain was re-introduced, and the culling algorithm proposed in this paper was employed to avoid unnecessary drawing overhead and achieve sparse super-sampling. Experimental results show that the algorithm in this paper can obtain the anti-aliasing effect comparable to the super-sampling algorithm, and achieve higher rendering efficiency, which can effectively avoid the problems of ghosting, blurring, flickering, and loss of sub-pixel details. 

Key words:  , temporal anti-aliasing algorithm, sparse, super-sampling, culling, reuse