Abstract: The method may include processing, by using a neural network, input feature maps of an image to obtain output feature maps of the image. The neural network may include a convolution part and/or a pooling part, and an aggregation part. The convolution part may include at least one parallel unit each of which contains two parallel paths, each path of the two parallel paths contains two cascaded convolution layers. The kernel sizes are 1 dimension and are different in different units. The pooling part includes at least one parallel unit each of which contains two parallel paths, each path of the two parallel paths contains two cascaded pooling layers. The size of filters of pooling is 1 dimension and is different in different units. The aggregation part is configured to concatenate results of the convolution part and/or the pooling part to obtain the output feature maps of the image.

Abstract: The method may include processing, by using a neural network, input feature maps of an image to obtain output feature maps of the image. The neural network may include a convolution part and/or a pooling part, and an aggregation part. The convolution part may include at least one parallel unit each of which contains two parallel paths, each path of the two parallel paths contains two cascaded convolution layers. The kernel sizes are 1 dimension and are different in different units. The pooling part includes at least one parallel unit each of which contains two parallel paths, each path of the two parallel paths contains two cascaded pooling layers. The size of filters of pooling is 1 dimension and is different in different units. The aggregation part is configured to concatenate results of the convolution part and/or the pooling part to obtain the output feature maps of the image.

Abstract: Embodiments of the present disclosure disclose methods and apparatus for removing turbid objects in an input image. The method comprising: dividing the input image into a first portion having a first transmittance and a second portion having a second transmittance; removing the turbid objects in the first portion using a first approach; removing the turbid objects in the second portion using a second approach; and combining the first portion in which the turbid objects are removed and the second portion in which the turbid objects are removed into an output image, wherein the first approach and the second approach are different and the first transmittance is greater than the second transmittance. The technical effect of the method and apparatus of the embodiments of the present disclosure is that the detail and texture of the objects in the image are better restored and the color distortion is smaller.

Abstract: Embodiments of the present disclosure disclose methods and apparatus for removing turbid objects in an input image. The method comprising: dividing the input image into a first portion having a first transmittance and a second portion having a second transmittance; removing the turbid objects in the first portion using a first approach; removing the turbid objects in the second portion using a second approach; and combining the first portion in which the turbid objects are removed and the second portion in which the turbid objects are removed into an output image, wherein the first approach and the second approach are different and the first transmittance is greater than the second transmittance. The technical effect of the method and apparatus of the embodiments of the present disclosure is that the detail and texture of the objects in the image are better restored and the color distortion is smaller.