Google Debuts Third-Gen AI for Turning Product Photos into 3D Shopping Models

• Google's new Veo-powered system can generate 360° product spins from as few as three images.
• The latest approach generalizes across categories like furniture, apparel, and electronics without requiring precise camera pose estimation.

Google has introduced a generative AI breakthrough that transforms flat product photos into interactive 3D shopping experiences. Built on Veo, the company’s advanced video generation model, this third-generation approach can produce high-fidelity, 360° spins of products from minimal image input. The technology is already live on Google Shopping, powering dynamic views of items such as shoes, furniture, and electronics.

Previous iterations relied on Neural Radiance Fields (NeRFs) and view-conditioned diffusion models, which required more images and complex pose estimation. These methods faced challenges with thin or detailed objects like sandals and heels. Veo simplifies this by using a curated dataset of synthetic 3D assets and learning to generate realistic video views conditioned on product images, capturing nuanced material and lighting effects.

Unlike its predecessors, the Veo-based method doesn't need accurate camera pose data and still manages to maintain visual coherence. With just a few images—ideally three covering most surfaces—it can create convincing, shoppable 3D renderings. A key differentiator is Veo’s ability to simulate intricate interactions of light, material, texture, and geometry, allowing for visually rich outputs that elevate the realism of digital product views. This marks a major step in making online shopping feel more like a tactile, in-store experience, with greater scalability for retailers.

🌀 Tom's Take

3D is a fundamental ingredient in spatial computing experiences, but as a new medium for most brands, creating 3D assets can be time-consuming and expensive. Google’s use of generative AI to transform existing assets—like video—into shoppable 3D renderings is the kind of breakthrough that can help more brands enter this next wave of computing.

Source: Google Research Blog