Amazon technologies, inc. (20240331211). GENERATING IMAGES OF SYNTHESIZED BODIES WEARING A GARMENT simplified abstract
Contents
GENERATING IMAGES OF SYNTHESIZED BODIES WEARING A GARMENT
Organization Name
Inventor(s)
Larry Davis of Brooklyn NY (US)
Nicolas Heron of New York NY (US)
Amit Kumar Agrawal of Santa Clara CA (US)
Nina Mitra Khosrowsalafi of Austin TX (US)
Osama Makansi of Nufringen (DE)
Oleksandr Vorobiov of Albstadt (DE)
GENERATING IMAGES OF SYNTHESIZED BODIES WEARING A GARMENT - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240331211 titled 'GENERATING IMAGES OF SYNTHESIZED BODIES WEARING A GARMENT
The abstract describes a system and method for generating images of synthesized bodies wearing a garment. A source image of a human or mannequin wearing a garment is submitted to a synthesized human generation system. The system classifies the image based on body types or orientations, segments the garment pixels, selects machine learning models, and generates output images of synthesized bodies wearing the garment.
- Source image of a human or mannequin wearing a garment is submitted to a synthesized human generation system.
- System classifies the image based on body types or orientations.
- Segmentation is applied to the source image to segment the garment pixels.
- Machine learning models are selected based on the classification of the source image.
- Output images of synthesized bodies wearing the garment are generated using the selected machine learning models.
Potential Applications: - Fashion industry for virtual try-on experiences - Online shopping platforms for showcasing garments on different body types - Virtual fitting rooms for personalized shopping experiences
Problems Solved: - Allows for realistic visualization of garments on different body types - Enhances the online shopping experience by providing accurate representations of how garments will look on individuals
Benefits: - Increases customer satisfaction by providing a more accurate depiction of how garments will fit - Reduces the need for physical try-ons, saving time and resources for both customers and retailers
Commercial Applications: Title: Virtual Try-On Technology for Enhanced Online Shopping Experiences Description: This technology can be utilized by e-commerce platforms, fashion brands, and virtual fitting room services to offer customers a more personalized and accurate shopping experience. By allowing users to virtually try on garments on synthesized bodies, retailers can increase sales and reduce returns.
Questions about Virtual Try-On Technology: 1. How does this technology impact the fashion industry's sustainability efforts? 2. What are the potential privacy concerns associated with using synthesized bodies for virtual try-on experiences?
Original Abstract Submitted
systems and methods are described for generating images of synthesized bodies wearing a garment. for instance, a source image of a human or mannequin wearing a garment may be submitted to a synthesized human generation system. in response to receiving the source image, the synthesized human generation system may use a classifier to classify the image as depicting one or more body types or orientations. the synthesized human generation system may also apply segmentation to the source image to segment the garment pixels. the synthesized human generation system may then select one or more body generation machine learning models based on the classification of the source image. the synthesized human generation system may utilize the selected machine learning models to generate one or more output images of synthesized bodies that appear to be wearing the garment, using the segmented garment as input.
