Neural reconstruction of sequential frames

摘要

In one embodiment, a computing system configured to generate a current frame may access a current sample dataset having incomplete pixel information of a current frame in a sequence of frames. The system may access a previous frame in the sequence of frames with complete pixel information. The system may further access a motion representation indicating pixel relationships between the current frame and the previous frame. The previous frame may then be transformed according to the motion representation. The system may generate the current frame having complete pixel information by processing the current sample dataset and the transformed previous frame using a first machine-learning model.