Gradient-Based Facial Texture Processing for Video Conferencing

A device, comprising:

• a memory;
• and
• a processor, the processor configured to execute instructions stored in the memory to:
• receive video content within a video communication session of a video communication platform, the video content having multiple video frames;
• receive, from a client device associated with a user, an appearance adjustment request:
• detect a face region within the video content;
• apply a smoothing process to low gradient parts of the face region, wherein the smoothing process is applied in a gradient;
• apply an edge-aware smoothing filter to the face region to preserve facial feature structures while smoothing areas adjacent to the facial feature structures;
• and
• generate a modified frame based on the applying of the smoothing process and the applying of the edge-aware smoothing filter.

A non-transitory computer-readable storage medium comprising instructions that, when executed by a processor, perform operations comprising:

• receiving video content within a video communication session of a video communication platform, the video content having multiple video frames;
• receiving, from a client device associated with a user, an appearance adjustment request;
• detecting a face region within the video content;
• applying a smoothing process to low gradient parts of the face region, wherein the smoothing process is applied in a gradient;
• applying an edge-aware smoothing filter to the face region to preserve facial feature structures while smoothing areas adjacent to the facial feature structures;
• and
• generating a modified frame based on the applying of the smoothing process and the applying of the edge-aware smoothing filter.