18243444. WHOLE BODY SEGMENTATION simplified abstract (Snap Inc.)
Contents
WHOLE BODY SEGMENTATION
Organization Name
Inventor(s)
Gal Dudovitch of Tel Aviv (IL)
Chia-Hao Hsieh of Los Angeles CA (US)
Sergei Korolev of Marina del Rey CA (US)
Ma'ayan Mishin Shuvi of Givatayim (IL)
WHOLE BODY SEGMENTATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18243444 titled 'WHOLE BODY SEGMENTATION
Simplified Explanation
The patent application describes methods and systems for enhancing monocular images of a user's whole body by applying visual effects based on a smoothed segmentation of the body.
- The system receives a monocular image of the user's whole body.
- It generates a segmentation of the body based on the monocular image.
- The system accesses a video feed containing previous monocular images.
- It uses the video feed to smooth the segmentation of the body generated from the monocular image.
- The system applies visual effects to the monocular image based on the smoothed segmentation.
Potential Applications
- Augmented reality applications that enhance the appearance of a user's body in real-time.
- Virtual try-on systems for clothing or accessories, where visual effects can be applied to the user's body to simulate different styles or designs.
- Fitness or wellness applications that provide visual feedback on body movements or posture.
Problems Solved
- Enhances the visual quality of monocular images by applying visual effects based on a smoothed segmentation of the user's body.
- Provides a more realistic and immersive experience in augmented reality or virtual try-on applications.
- Enables accurate tracking and analysis of body movements or posture in fitness or wellness applications.
Benefits
- Improved visual appearance of monocular images by applying visual effects based on a smoothed segmentation.
- Real-time application of visual effects allows for interactive and dynamic user experiences.
- Accurate tracking and analysis of body movements or posture can provide valuable feedback for fitness or wellness applications.
Original Abstract Submitted
Methods and systems are disclosed for performing operations comprising: receiving a monocular image that includes a depiction of a whole body of a user; generating a segmentation of the whole body of the user based on the monocular image; accessing a video feed comprising a plurality of monocular images received prior to the monocular image; smoothing, using the video feed, the segmentation of the whole body generated based on the monocular image to provide a smoothed segmentation; and applying one or more visual effects to the monocular image based on the smoothed segmentation.
