This position paper argues for the use of \emph{structured generative models} (SGMs) for scene understanding. This requires the reconstruction of a 3D scene from an input image, whereby the contents of the image are causally explained in terms of models of instantiated objects, each with their own type, shape, appearance and pose, along with global variables like scene lighting and camera parameters. This approach also requires scene models which account for the co-occurrences and inter-relationships of objects in a scene. The SGM approach has the merits that it is compositional and generative, which lead to interpretability. To pursue the SGM agenda, we need models for objects and scenes, and approaches to carry out inference. We first review models for objects, which include ``things'' (object categories that have a well defined shape), and ``stuff'' (categories which have amorphous spatial extent). We then move on to review \emph{scene models} which describe the inter-relationships of objects. Perhaps the most challenging problem for SGMs is \emph{inference} of the objects, lighting and camera parameters, and scene inter-relationships from input consisting of a single or multiple images. We conclude with a discussion of issues that need addressing to advance the SGM agenda.
翻译:此位置文件 论证使用 emph{ 结构化基因模型} (SGMs) 进行现场理解 。 这需要从输入图像中重建 3D 场景 。 这需要从输入图像中重建 3D 场景, 从而将图像的内容以瞬间物体的模型、 每种类型、 形状、 外观和布局, 以及全球变量, 如场景照明和摄像参数 。 此方法还要求以场景中物体的共生和相互关系为根据的场景模型。 SGM 方法的优点是, 它的构成和基因化, 导致可解释性。 为了追求 SGM 议程, 我们需要对象和场景的模型, 以及进行推断的方法。 我们首先审查对象的模型, 包括“ 瞬间物体 ” ( 对象类别, 形状很明确), 和“ 星座” ( 空间范围不固定的星座 ) 。 我们接着审查 描述天体间关系模型 的 。 也许, 最具有挑战性的物体 与摄像头 的图像 的预变变变 。