Related papers: GRAINS: Generative Recursive Autoencoders for INdo…

We train generative 'up-convolutional' neural networks which are able to generate images of objects given object style, viewpoint, and color. We train the networks on rendered 3D models of chairs, tables, and cars. Our experiments show that…

Graph Convolutional Networks (GCNs) are powerful models for node representation learning tasks. However, the node representation in existing GCN models is usually generated by performing recursive neighborhood aggregation across multiple…

Inverse graphics aims to recover 3D models from 2D observations. Utilizing differentiable rendering, recent 3D-aware generative models have shown impressive results of rigid object generation using 2D images. However, it remains challenging…

Novel View Synthesis (NVS) from unconstrained photo collections is challenging in computer graphics. Recently, 3D Gaussian Splatting (3DGS) has shown promise for photorealistic and real-time NVS of static scenes. Building on 3DGS, we…

We present a novel artificial cognitive mapping system using generative deep neural networks, called variational autoencoder/generative adversarial network (VAE/GAN), which can map input images to latent vectors and generate temporal…

Recent progress in NeRF-based GANs has introduced a number of approaches for high-resolution and high-fidelity generative modeling of human heads with a possibility for novel view rendering. At the same time, one must solve an inverse…

We introduce the concept of a Graph-Informed Neural Network (GINN), a hybrid approach combining deep learning with probabilistic graphical models (PGMs) that acts as a surrogate for physics-based representations of multiscale and…

Implicit neural representation has demonstrated promising results in 3D reconstruction on various scenes. However, existing approaches either struggle to model fast-moving objects or are incapable of handling large-scale camera ego-motions…

Comprehending natural language instructions is a charming property for 3D indoor scene synthesis systems. Existing methods directly model object joint distributions and express object relations implicitly within a scene, thereby hindering…

A long-standing question for urban and regional planners pertains to the ability to describe urban patterns quantitatively. Cities' transport infrastructure, particularly street networks, provides an invaluable source of information about…

We propose Tree Variational Autoencoder (TreeVAE), a new generative hierarchical clustering model that learns a flexible tree-based posterior distribution over latent variables. TreeVAE hierarchically divides samples according to their…

Recent architectural developments have enabled recurrent neural networks (RNNs) to reach and even surpass the performance of Transformers on certain sequence modeling tasks. These modern RNNs feature a prominent design pattern: linear…

Heterogeneous information networks (HINs) can be used to model various real-world systems. As HINs consist of multiple types of nodes, edges, and node features, it is nontrivial to directly apply graph neural network (GNN) techniques in…

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…

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential…

Gastrointestinal (GI) imaging via Wireless Capsule Endoscopy (WCE) generates a large number of images requiring manual screening. Deep learning-based Clinical Decision Support (CDS) systems can assist screening, yet their performance relies…

While objects from different categories can be reliably decoded from fMRI brain response patterns, it has proved more difficult to distinguish visually similar inputs, such as different instances of the same category. Here, we apply a…

Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the…

Automatic scene generation is an essential area of research with applications in robotics, recreation, visual representation, training and simulation, education, and more. This survey provides a comprehensive review of the current…

Generative models have emerged as powerful tools in medical imaging, enabling tasks such as segmentation, anomaly detection, and high-quality synthetic data generation. These models typically rely on learning meaningful latent…