Multi-Plane Program Induction with 3D Box Priors

Perspective Plane Program Induction from a Single Image

We study the inverse graphics problem of inferring a holistic representation for natural images. Given an input image, our goal is to induce a neuro-symbolic, program-like representation that jointly models camera poses, object locations, and global scene structures. Such high-level, holistic scene representations further facilitate low-level image manipulation tasks such as inpainting. We formulate this problem as jointly finding the camera pose and scene structure that best describe the input image. The benefits of such joint inference are two-fold: scene regularity serves as a new cue for p…

From explanation to synthesis: Compositional program induction for learning from demonstration

Hybrid systems are a compact and natural mechanism with which to address problems in robotics. This work introduces an approach to learning hybrid systems from demonstrations, with an emphasis on extracting models that are explicitly verifiable and easily interpreted by robot operators. We fit a sequence of controllers using sequential importance sampling under a generative switching proportional controller task model. Here, we parameterise controllers using a proportional gain and a visually verifiable joint angle goal. Inference under this model is challenging, but we address this by introdu…

视觉概念学习中的组合多样性

Compositional diversity in visual concept learning

本文研究人类在视觉概念学习中的组合泛化能力，提出贝叶斯程序归纳模型和神经符号程序归纳模型，在少样本分类与生成任务中揭示人类和模型如何从已有部件组合出新概念并产生多样化行为。