创建 3D 模型然后确定尺寸
是否有任何库可以拍摄一些物体的数码照片并创建它的 3D 模型。
例如，理想情况下，我想让用户上传一个物体的 n 张图片，并将这些图片输入到 photosynth 之类的东西中来构建模型，然后确定该物体的尺寸。
想法？
Are there any libraries that can take a few digital pictures of an object and create a 3d model of it.
For instance, I'd ideally like to let a user upload n pictures of an object and feed the pictures into something like photosynth to construct a model, then determine dimensions of said object.
Thoughts?
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（1）
你所说的是深度映射，或“视差映射”，它是立体计算机视觉的基础。 OpenCV 项目有执行此操作的库。 我不知道它们是否直接转换为可旋转的 3D 对象，这可能就是您正在寻找的，但它们可能很接近。
http://opencv.willowgarage.com/wiki/
http://en.wikipedia.org/wiki/OpenCV
尺寸部分有点难。 这些库可以识别对象，但这只会为您提供“通用”维度。 如果您使用两个相机的立体成像，您可以从多个样本中确定真实的深度，从而确定尺寸。
这个问题很难，真的很难，否则（即不可能。）
What you're talking about is depth mapping, or 'disparity mapping', which is the basis of stereoscopic computer vision. The OpenCV project has libraries which do this. I don't know if they directly convert into a rotatable 3D object, which may be what you are looking for, but they probably come close.
http://opencv.willowgarage.com/wiki/
http://en.wikipedia.org/wiki/OpenCV
The dimension part is a little harder. The libraries can identify objects, but that would just give you 'common' dimension. If you were using stereoscopic imaging with two cameras, you could determine real depth, and therefore dimensions, from multiple samples.
The problem is difficult, really difficult, otherwise (i.e., impossible.)