Google DeepMind has introduced a new AI-powered feature for Google Photos called Auto frame, which allows users to re-compose images after they have been taken. The system first estimates a 3D scene and camera perspective from the original photo. It then uses generative AI, specifically a latent diffusion model, to fill in any newly revealed areas and create an authentic new perspective of the scene. AI
影响 Enhances user control over photo composition post-capture, potentially reducing the need for manual editing or retakes.
排序理由 This is a feature update to an existing product, not a new model release or paradigm-shifting capability.
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
