WANNA by Perfect Corp. is Launching a Shoulder Try-On Feature, the Latest Addition to its Bags Virtual Try-On Experience

WANNA, a leading provider of fashion AR virtual try-on solutions and a brand of Perfect Corp. (NYSE: PERF), announces the launch of its shoulder try-on feature, a new addition to the Bags Virtual Try-On experience. The feature lets shoppers see how a bag looks when worn on the shoulder, complementing the existing crossbody try-on. It allows customers to replicate the real in-store experience by trying on the bag in different ways, virtually style the bag with their outfits, assess its proportions, and make confident purchasing decisions anytime, anywhere.

Developing a realistic and stable shoulder virtual try-on presented a unique technical challenge: ensuring the bag remains correctly positioned even as users turn sideways to check proportions and outfit matching in the mirror. WANNA addresses this with a proprietary AI-powered engine built to perform in real-time:

Real-Time Pose Estimation

Precise 3D body tracking with low latency is essential for natural bag placement. WANNA’s system uses highly optimized neural architectures specifically designed for mobile devices, balancing speed, accuracy, and energy efficiency to deliver real-time 3D pose and joint estimation - at frame rates fast enough to keep up with user movement.

Segmentation & Occlusion Handling

One of the hardest challenges in AR is determining when a virtual object should be partially hidden behind real-world elements like arms or hands. WANNA’s AI handles these scenarios with intelligent segmentation and depth-aware modeling, ensuring realistic layering and preventing unnatural overlaps.

Advanced Temporal Smoothing for Seamless Motion

Frame-to-frame inconsistencies in pose estimation can cause flickering or instability in object placement. WANNA’s temporal smoothing algorithms employ advanced filtering techniques to deliver seamless, fluid motion, enabling the virtual bag to move naturally with the user, particularly in video mode.

Multiple View Support

Works in selfie mode, mirror view, and side perspectives, maintaining correct positioning and scale across camera modes for a fully immersive virtual try-on experience.

Behind this technology is a powerful data engine: a proprietary dataset of 487,000 training images, including 169,000 manually labeled, 127,000 AI-synthesized, and 190,000 pseudo-labeled samples. This large-scale, diverse dataset — spanning different body types, lighting conditions, and angles — was critical in training the system to deliver accurate and visually consistent results across product styles and real-world usage scenarios.

WANNA fine-tuned the shoulder try-on experience based on extensive user research with luxury shoppers, ensuring a realistic and valuable tool for online purchases. Before rolling out the feature, WANNA conducted usability testing, where high-end consumers highlighted its accuracy and realism.

Zina Grossman, Head of Growth at WANNA, said:
"Fashion consumers expect digital shopping experiences as engaging and detailed as in-store interactions. With the shoulder try-on feature launch, we’re refining how bags are showcased online and delivering an intuitive and memorable shopping experience."

Alice Chang, CEO of Perfect Corp. and WANNA, said:
"At Perfect Corp., we are committed to pushing the boundaries of AR virtual try-on in fashion retail. The addition of shoulder try-on to WANNA’s Bags Virtual Try-On suite is a testament to our dedication to innovation. By delivering hyper-realistic virtual experiences, we are empowering brands to engage with customers in meaningful ways, bridging the gap between digital and physical retail."

WANNA VTO for Bags is designed for seamless web integration, ensuring broad accessibility across all digital platforms. The technology easily integrates into e-commerce websites, allowing brands to enhance engagement without additional software requirements. Moreover, WANNA Virtual Try-On is optimized for digital marketing, with shareable links that can be embedded into newsletters, Instagram, WeChat, and TikTok campaigns, driving interaction and product visibility. WANNA Virtual Try-On for Bags is now available via SDK integration.