Embodiments of this application disclose an image processing method and an electronic apparatus, to process a video image based on photographing environment brightness. The image processing method includes: detecting photographing environment brightness during video photographing; and when the photographing environment brightness is less than a preset threshold, processing a video image by using a neural network; or when the photographing environment brightness is greater than or equal to a preset threshold, processing a video image by using a preset denoising method, where the preset denoising method does not include a neural network architecture. A neural network in the artificial intelligence (artificial intelligence, AI) field requires a large quantity of computing units. This causes power consumption. According to the foregoing image processing method, a video image processing effect can be improved while power consumption of a terminal is ensured.