谷歌新推出的引导视觉功能可帮助你阅读细则

qimuai 发布于 阅读:45 一手编译

谷歌新推出的引导视觉功能可帮助你阅读细则

内容来源:https://www.theverge.com/ai-artificial-intelligence/1003756/google-gemini-live-guided-vision

内容总结:

谷歌近日在兼容的安卓设备上推出了一项名为“引导视觉”(Guided Vision)的新功能,该功能已集成至Gemini Live。用户可通过手机摄像头实时获取人工智能生成的音频描述,识别眼前物体、阅读细小文字、描述周围环境等。该功能主要面向视障人士及需要特定场景辅助的用户,类似于苹果在iPhone和Vision Pro上推出的VoiceOver实时识别功能。

除Gemini应用外,该功能也可在谷歌TalkBack中使用,运行安卓9及以上系统的用户还可在设置中为其配置无障碍快捷方式。用户可针对所拍摄的画面继续追问,例如让Gemini读出所找到物品的保质期。若用户询问的物体不在镜头内,Gemini会通过音频提示帮助调整摄像头方向。

谷歌同时提醒用户,不要将“引导视觉”用于导航、安全出行指引或障碍物检测等用途,也不应将其替代手杖或其他行动辅助工具。

中文翻译:

Guided Vision 今日在兼容的 Android 设备上于 Gemini Live 中上线,利用 AI 对你手机摄像头所对准的任何物体进行实时音频描述。在 Gemini Live 中分享你的摄像头画面后,你可以让 Google 的 AI 帮你完成诸如阅读小字、描述周围环境、寻找或识别身边物体,以及描述特定物体细节等任务。

Google 全新 Guided Vision 功能可帮你读懂细则小字

低视力人群可以使用 Guided Vision 让 Gemini 描述附近的事物,并提出后续问题。

低视力人群可以使用 Guided Vision 让 Gemini 描述附近的事物,并提出后续问题。

与 Apple 为 iPhone 和 Vision Pro 添加的 VoiceOver 实时识别功能类似,它专为失明、低视力人群或希望在特定场景中获得辅助的人设计。除了 Gemini 应用外,Guided Vision 也可在 Google TalkBack 中使用,用户还可以在运行 Android 9 及以上版本的设备上通过“设置”应用为其设置无障碍快捷键——此前该功能已在一系列 Pixel 更新公告中亮相。

你还可以针对正在查看的任何内容提出后续问题,比如让 Gemini 读出它帮你找到的物品上的保质期。Google 表示,如果你询问的东西不在画面中,Gemini 会给出音频提示,帮你调整摄像头对准。不过,Google 提醒用户不要将 Guided Vision 用于“导航、安全出行指引或障碍物检测”等用途,也不要将其作为手杖或行动辅助工具的替代品。

热门内容

英文来源:

Guided Vision is launching in Gemini Live on compatible Android devices today to use AI to give real-time audio descriptions of anything you point your phone’s camera at. By sharing your camera in Gemini Live, you can have Google’s AI help with things like reading small text, describing your surroundings, finding or identifying objects around you, and describing details on specific objects.
Google’s new Guided Vision feature can help you read the fine print
People with low vision can use Guided Vision to have Gemini describe what’s nearby and ask follow-up questions.
People with low vision can use Guided Vision to have Gemini describe what’s nearby and ask follow-up questions.
Like the VoiceOver Live Recognition feature Apple has added to the iPhone and Vision Pro, it’s designed for people who are blind, have low vision, or want assistance in specific situations. In addition to the Gemini app, Guided Vision is also available in Google TalkBack, or users can set up an accessibility shortcut for it in the Settings app on devices running Android 9 and above, after it was announced in a recent set of Pixel updates.
You can also ask follow-up questions about whatever you’re looking at, like asking Gemini to read off the expiration date on an item it helped you find. Google says Gemini will give you audio cues to help line up your camera if you ask about something that’s not in the shot. However, Google cautions users not to rely on Guided Vision for things like “navigation, safe-travel guidance, or obstacle detection,” or as a replacement for a cane or mobility aid.
Most Popular

ThevergeAI大爆炸

文章目录


    扫描二维码,在手机上阅读