Abstract: A method and apparatus for processing a video is provided. A current image frame of a video and a mask for a first area are obtained. The Image included in the first area is to be removed from the current image frame. A first resultant image of the current image frame is obtained with an image processing network based on the current image frame and the mask. The first resultant image is an image from which the image included in the first area is removed from the current image frame. A second resultant image of a previous image frame of the current image frame is obtained. The second resultant image is an image from which the image included in the second area is removed from the previous image frame. A final resultant image of the current image frame is obtained by fusing the first resultant image and the second resultant image.

Abstract: A method and apparatus for processing a video is provided. A current image frame of a video and a mask for a first area are obtained. The Image included in the first area is to be removed from the current image frame. A first resultant image of the current image frame is obtained with an image processing network based on the current image frame and the mask. The first resultant image is an image from which the image included in the first area is removed from the current image frame. A second resultant image of a previous image frame of the current image frame is obtained. The second resultant image is an image from which the image included in the second area is removed from the previous image frame. A final resultant image of the current image frame is obtained by fusing the first resultant image and the second resultant image.

Abstract: A method for determining exposure levels of an image-sensor pixel array includes (a) storing a first plurality of pixel values representing a first captured image, captured with the image sensor in an applied exposure configuration, each distinct region of the pixel array having a respective first exposure level, (b) determining pixel-value global statistics, (c) estimating, from the global statistics, a global pixel value of the first captured image, (d) determining, for each distinct region, a respective local statistics of the first pixel values, (e) assigning, to each distinct region, a respective scale factor based on the local statistics of the distinct region, (f) determining a refined exposure configuration including, for each distinct region, a second exposure level proportional to a product of its respective first exposure level and its respective scale factor, and (g) capturing second pixel values with the image sensor configured in the refined exposure configuration.

Abstract: A method for determining exposure levels of an image-sensor pixel array includes (a) storing a first plurality of pixel values representing a first captured image, captured with the image sensor in an applied exposure configuration, each distinct region of the pixel array having a respective first exposure level, (b) determining pixel-value global statistics, (c) estimating, from the global statistics, a global pixel value of the first captured image, (d) determining, for each distinct region, a respective local statistics of the first pixel values, (e) assigning, to each distinct region, a respective scale factor based on the local statistics of the distinct region, (f) determining a refined exposure configuration including, for each distinct region, a second exposure level proportional to a product of its respective first exposure level and its respective scale factor, and (g) capturing second pixel values with the image sensor configured in the refined exposure configuration.