> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/vision.md).

# 视觉

Vision 赋予 Convai 角色查看你 Unity 场景中正在发生的事情的能力。帧源可从 Unity 相机、物理摄像头或 Meta Quest 透传画面中捕获图像，SDK 会通过 WebRTC 将其与音频对话一起流式传输到 Convai。

### 平台支持

| 平台                | 支持的帧源                                                | 说明                                                              |
| ----------------- | ---------------------------------------------------- | --------------------------------------------------------------- |
| PC / Mac / 主机     | `CameraVisionFrameSource`, `WebcamVisionFrameSource` | 完整 RenderTexture 管线；最高 30 fps                                   |
| Android / iOS     | `CameraVisionFrameSource`, `WebcamVisionFrameSource` | Webcam 源在启动时请求摄像头权限                                             |
| WebGL             | *（Canvas，自动）*                                        | `canvas.captureStream()` 路径 — 无需帧源组件；帧率上限为 15 fps； **需要 HTTPS** |
| Meta Quest 3 / 3S | `QuestVisionFrameSource`                             | 需要 Meta XR SDK 和 `horizonos.permission.HEADSET_CAMERA`          |

{% hint style="info" %}
Vision 需要 `ConvaiRoomManager.Connection Type` 设置为 **Video**。如果它设置为 `音频`, `ConvaiVisionPublisher` 无论其他组件如何配置，都会保持空闲。
{% endhint %}

{% hint style="danger" %}
**WebGL：需要 HTTPS。** 该 `canvas.captureStream()` API 会被浏览器在非 HTTPS 源上阻止。 `http://localhost` 是唯一的例外。在生产环境中测试 Vision 之前，请将你的 WebGL 构建部署到 HTTPS 主机上。
{% endhint %}

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Vision 的工作原理</strong><br>了解管线架构、关键概念、组件放置以及启动顺序。</td><td><a href="/pages/6ebd5ccda4df347e0fb3db3967023f01c8054427">/pages/6ebd5ccda4df347e0fb3db3967023f01c8054427</a></td></tr><tr><td><strong>动态视觉上下文</strong><br>启用帧采样，使角色基于缓冲帧进行推理，而不是处理每一帧新到达的画面，使用与动态上下文相同的响应模式词汇。</td><td><a href="/pages/4290d3b5bc8fff8787b36689dbdf110d6ebc4c11">/pages/4290d3b5bc8fff8787b36689dbdf110d6ebc4c11</a></td></tr><tr><td><strong>Vision 快速入门</strong><br>通过逐步的 Inspector 引导，让角色接收实时摄像头画面——无需代码。</td><td><a href="/pages/8688e51bd7c568104d68e6f3c42a8d7ef8b881e8">/pages/8688e51bd7c568104d68e6f3c42a8d7ef8b881e8</a></td></tr><tr><td><strong>Vision 帧源</strong><br>为每个平台和使用场景配置 CameraVisionFrameSource、WebcamVisionFrameSource 和 QuestVisionFrameSource。</td><td><a href="/pages/3c41ddceb11fc2af6b830a08a48c437b590c8882">/pages/3c41ddceb11fc2af6b830a08a48c437b590c8882</a></td></tr><tr><td><strong>发布策略</strong><br>选择发布策略，调整帧率和比特率，并了解包括 WebGL 在内的平台特定行为。</td><td><a href="/pages/b15c237537e3521d8e360ca90de5e9b15be340ec">/pages/b15c237537e3521d8e360ca90de5e9b15be340ec</a></td></tr><tr><td><strong>Vision 调试预览</strong><br>将当前活动的帧源可视化为屏幕叠加层，并在 Editor 中监控捕获状态。</td><td><a href="/pages/885a0e6676256e7738207107695532701ef9b1ec">/pages/885a0e6676256e7738207107695532701ef9b1ec</a></td></tr><tr><td><strong>自定义帧源</strong><br>实现 IVisionFrameSource 以发布任何自定义视频管线——接口约定、Y 轴翻转要求以及最小实现。</td><td><a href="/pages/cb7758289bc48a93210bce51933fd819fd05e245">/pages/cb7758289bc48a93210bce51933fd819fd05e245</a></td></tr><tr><td><strong>Vision 脚本 API</strong><br>ConvaiVisionPublisher 的属性和方法、运行时状态监控，以及用于分析集成的领域事件。</td><td><a href="/pages/9ee175b12da238182d707abd778abdc3a8706c80">/pages/9ee175b12da238182d707abd778abdc3a8706c80</a></td></tr><tr><td><strong>Vision 使用示例</strong><br>面向安全培训、设备上手、VR 演示和手动触发会话的端到端示例。</td><td><a href="/pages/c296dab9e1d439fdd895aa80e239915e6c1d0943">/pages/c296dab9e1d439fdd895aa80e239915e6c1d0943</a></td></tr><tr><td><strong>排查 Vision 问题</strong><br>使用结构化检查清单和决策树诊断发布失败、空白画面、权限错误和平台特定问题。</td><td><a href="/pages/86612bc613c5a299a468b71b3fb8a40e625ee1fe">/pages/86612bc613c5a299a468b71b3fb8a40e625ee1fe</a></td></tr></tbody></table>

### 动态视觉上下文

动态视觉上下文使 Convai 能够持续从已发布的视频轨道中采样到滚动帧缓冲区，并将最新的帧附加到角色的轮次中，而不是在每一帧到达时都作出反应。它与以下内容共享其响应模式词汇： [动态上下文](/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/dynamic-context.md): `ConvaiRespondMode` 值 `Silent`, `Auto`，以及 `MustRespond` 决定新输入是否发言、是否由模型决定，或者是否保持静默。请参见 [动态上下文脚本 API](/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/dynamic-context/dynamic-context-scripting-api.md) 以获取完整的 `ConvaiRespondMode` 参考信息。

### 下一步

从以下内容开始： [Vision 快速入门](/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/vision/quick-start.md) 以从场景摄像头获取可工作的流，然后使用 [Vision 帧源](/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/vision/frame-sources.md) 以为你的平台选择正确的捕获方法。有关管线细节，请参见 [Vision 的工作原理](/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/vision/how-vision-works.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/features/vision.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.