To provide an image generation apparatus that generates a visually-favorable target video sequence in color using input video sequences of color components and that is least likely to have an insufficient transfer rate when obtaining the input video sequences. The image generation apparatus includes: an image receiving unit (101) that receives, as the plurality of input video sequences, a plurality of video sequences that are obtained by shooting the same subject with a phase difference being set between frame exposure periods of the different color components; and a color image integration unit (103) that generates the target video sequence whose frame cycle is shorter than each of the frame exposure periods of the input video sequences, by reducing a difference between a frame image of the input video sequence of each color component and a sum of a plurality of frame images of the target video sequence which are included in a period that corresponds to the frame image of the input video sequence.