相关论文: Structured Graph Variational Autoencoders for Indo…

Despite significant recent progress on generative models, controlled generation of images depicting multiple and complex object layouts is still a difficult problem. Among the core challenges are the diversity of appearance a given object…

Deep generative models for graphs have exhibited promising performance in ever-increasing domains such as design of molecules (i.e, graph of atoms) and structure prediction of proteins (i.e., graph of amino acids). Existing work typically…

Generating coherent and useful image/video scenes from a free-form textual description is technically a very difficult problem to handle. Textual description of the same scene can vary greatly from person to person, or sometimes even for…

Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation…

Data-driven approaches have become a dominant paradigm for robotic grasp planning. However, the performance of these approaches is enormously influenced by the quality of the available training data. In this paper, we propose a framework to…

It is common in graphic design humans visually arrange various elements according to their design intent and semantics. For example, a title text almost always appears on top of other elements in a document. In this work, we generate…

We develop a framework for incorporating structured graphical models in the \emph{encoders} of variational autoencoders (VAEs) that allows us to induce interpretable representations through approximate variational inference. This allows us…

Recent approaches have achieved great success in image generation from structured inputs, e.g., semantic segmentation, scene graph or layout. Although these methods allow specification of objects and their locations at image-level, they…

Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic…

Computational imaging is increasingly vital for a broad spectrum of applications, ranging from biological to material sciences. This includes applications where the object is known and sufficiently sparse, allowing it to be described with a…

Recent text-to-scene generation approaches largely reduced the manual efforts required to create 3D scenes. However, their focus is either to generate a scene layout or to generate objects, and few generate both. The generated scene layout…

We introduce SceneLinker, a novel framework that generates compositional 3D scenes via semantic scene graph from RGB sequences. To adaptively experience Mixed Reality (MR) content based on each user's space, it is essential to generate a 3D…

Continuously-observed event occurrences, often exhibit self- and mutually-exciting effects, which can be well modeled using temporal point processes. Beyond that, these event dynamics may also change over time, with certain periodic trends.…

We propose and demonstrate a generative deep learning approach for the shape recognition of an arbitrary object from its acoustic scattering properties. The strategy exploits deep neural networks to learn the mapping between the latent…

Despite the recent advancement of Generative Adversarial Networks (GANs) in learning 3D-aware image synthesis from 2D data, existing methods fail to model indoor scenes due to the large diversity of room layouts and the objects inside. We…

A key goal of unsupervised learning is to go beyond density estimation and sample generation to reveal the structure inherent within observed data. Such structure can be expressed in the pattern of interactions between explanatory latent…

Most previous work on neural text generation from graph-structured data relies on standard sequence-to-sequence methods. These approaches linearise the input graph to be fed to a recurrent neural network. In this paper, we propose an…

Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distributed vertex locations of a predetermined graph through a series of graph convolutions, leading to…

Generative models have shown great promise in synthesizing photorealistic 3D objects, but they require large amounts of training data. We introduce SinGRAF, a 3D-aware generative model that is trained with a few input images of a single…

Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…