Maintaining neighboring contextual awareness with zoom

1 . A method comprising:

identifying an area of interest within a visual output of a surgical site;

performing a zoom operation on the area of interest to generate a magnified area of interest;

determining, based on an amount of zoom associated with the zoom operation, an occluded region around the area of interest within the visual output, wherein the occluded region is a region of the visual output generated based on a difference between the magnified area of interest and the area of interest within the visual output prior to performing the zoom operation;

applying a non-linear compression to the occluded region of the visual output to generate a compression zone within the magnified area of interest, wherein the compression zone has a magnification that varies based on radial distance, an inner portion of the compression zone having a first magnification based on a magnification of the magnified area of interest and an outer portion of the compression zone having a second magnification based on a magnification of a remainder of the visual output; and

updating the magnified area of interest by replacing at least one pixel of the occluded region with at least one pixel of the compression zone.

2 . The method of claim 1 , wherein the visual output of the surgical site is an image.

3 . The method of claim 1 , wherein identifying the area of interest within the visual output of the surgical site includes cropping the area of interest from the visual output of the surgical site.

4 . The method of claim 3 , further comprising:

stitching the magnified area of interest comprising the compression zone to the visual output of the surgical site.

5 . The method of claim 1 , wherein the visual output of the surgical site is one frame of a video of the surgical site, and wherein the identifying, the performing, the determining, the applying, the updating are performed for a plurality of frames of the video.

6 . The method of claim 5 , wherein the video is a live feed of the surgical site, the method further comprising:

outputting the live feed of the video comprising the visual output and the magnified area of interest.

7 . The method of claim 1 , wherein applying non-linear compression to the occluded region comprises:

obtaining, based on the zoom operation, a scale factor;

determining a zoom area percentage based on a radius between a center of the magnified area of interest and a radius of the magnified area of interest;

determining, based on the zoom area percentage and the scale factor, a power coefficient;

for each pixel of the occluded region, determining, based on the power coefficient, a new pixel value for the respective pixel; and

updating the respective pixel with the new pixel value.

8 . The method of claim 7 , wherein determining the new pixel value includes obtaining polar coordinates of the respective pixel, determining a new radius value by applying the power coefficient to a radius value of the polar coordinates of the respective pixel, and obtaining, based on the new radius value, cartesian coordinates of the new pixel.

9 . A system comprising:

an image capture device configured to acquire at least one frame of a surgical site; and

one or more processors, operatively coupled to the image capture device, the one or more processors to perform operations comprising:

identifying, based on the at least one frame of the surgical site, an area of interest within a visual output of the surgical site;

performing a zoom operation on the area of interest to generate a magnified area of interest;

determining, based on an amount of zoom associated with the zoom operation, an occluded region around the area of interest within the visual output, wherein the occluded region is a region of the visual output generated based on a difference between the magnified area of interest and the area of interest within the visual output prior to performing the zoom operation;

applying a non-linear compression to the occluded region of the visual output to generate a compression zone within the magnified area of interest, wherein the compression zone has a magnification that varies based on radial distance, an inner portion of the compression zone having a first magnification based on a magnification of the magnified area of interest and an outer portion of the compression zone having a second magnification based on a magnification of a remainder of the visual output; and

updating the magnified area of interest by replacing at least one pixel of the occluded region with at least one pixel of the compression zone.

10 . The system of claim 9 , wherein the visual output of the surgical site is an image.

11 . The system of claim 9 , wherein identifying the area of interest within the visual output of the surgical site includes cropping the area of interest from the visual output of the surgical site.

12 . The system of claim 11 , wherein the one or more processors is to perform further operations comprising:

stitching the magnified area of interest comprising the compression zone to the visual output of the surgical site.

13 . The system of claim 9 , wherein the at least one frame associated with the visual output of the surgical site is a frame of a video of the surgical site, and wherein the identifying, the performing, the determining, the applying, the updating are performed for a plurality of frames of the video.

14 . The system of claim 13 , wherein the video is a live feed of the surgical site, the one or more processors to perform operations further comprising:

outputting the live feed of the video comprising the visual output and the magnified area of interest.

15 . The system of claim 9 , wherein applying non-linear compression to the occluded region comprises:

obtaining, based on the zoom operation, a scale factor;

determining a zoom area percentage based on a radius between a center of the magnified area of interest and a radius of the magnified area of interest;

determining, based on the zoom area percentage and the scale factor, a power coefficient;

for each pixel of the occluded region, determining, based on the power coefficient, a new pixel value for the respective pixel; and

updating the respective pixel with the new pixel value.

16 . The system of claim 15 , wherein determining the new pixel value includes obtaining polar coordinates of the respective pixel, determining a new radius value by applying the power coefficient to a radius value of the polar coordinates of the respective pixel, and obtaining, based on the new radius value, cartesian coordinates of the new pixel.

17 . A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

identifying an area of interest within a visual output of a surgical site;

performing a zoom operation on the area of interest to generate a magnified area of interest;

determining, based on an amount of zoom associated with the zoom operation, an occluded region around the area of interest within the visual output, wherein the occluded region is a region of the visual output generated based on a difference between the magnified area of interest and the area of interest within the visual output prior to performing the zoom operation;

applying a non-linear compression to the occluded region of the visual output to generate a compression zone within the magnified area of interest, wherein the compression zone has a magnification that varies based on radial distance, an inner portion of the compression zone having a first magnification based on a magnification of the magnified area of interest and an outer portion of the compression zone having a second magnification based on a magnification of a remainder of the visual output; and

updating the magnified area of interest by replacing at least one pixel of the occluded region with at least one pixel of the compression zone.

18 . The non-transitory computer-readable storage medium of claim 17 , wherein applying non-linear compression to the occluded region comprises:

obtaining, based on the zoom operation, a scale factor;

determining a zoom area percentage based on a radius between a center of the magnified area of interest and a radius of the magnified area of interest;

determining, based on the zoom area percentage and the scale factor, a power coefficient;

for each pixel of the occluded region, determining, based on the power coefficient, a new pixel value for the respective pixel; and

updating the respective pixel with the new pixel value.

19 . The non-transitory computer-readable storage medium of claim 17 , wherein identifying the area of interest within the visual output of a surgical site includes cropping the area of interest from the visual output of the surgical site.

20 . The non-transitory computer-readable storage medium of claim 17 , wherein the visual output of the surgical site is one frame of a video of the surgical site, and wherein the identifying, the performing, the determining, the applying, the updating are performed for a plurality of frames of the video.