Related papers: Locally Masked Convolution for Autoregressive Mode…
Deformable image registration (alignment) is highly sought after in numerous clinical applications, such as computer aided diagnosis and disease progression analysis. Deep Convolutional Neural Network (DCNN)-based image registration methods…
Deep neural networks can learn powerful prior probability models for images, as evidenced by the high-quality generations obtained with recent score-based diffusion methods. But the means by which these networks capture complex global…
Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences indistinguishably among 3D points, arising an intrinsic…
We present highly efficient algorithms for performing forward and backward propagation of Convolutional Neural Network (CNN) for pixelwise classification on images. For pixelwise classification tasks, such as image segmentation and object…
Recently, there has been a growing interest in predicting human motion, which involves forecasting future body poses based on observed pose sequences. This task is complex due to modeling spatial and temporal relationships. The most…
Depth completion is a critical task for handling depth images with missing pixels, which can negatively impact further applications. Recent approaches have utilized Convolutional Neural Networks (CNNs) to reconstruct depth images with the…
Autoregressive models have emerged as a powerful generative paradigm for visual generation. The current de-facto standard of next token prediction commonly operates over a single-scale sequence of dense image tokens, and is incapable of…
Recently deep generative models have achieved impressive progress in modeling the distribution of training data. In this work, we present for the first time a generative model for 4D light field patches using variational autoencoders to…
Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to…
In this age of information, images are a critical medium for storing and transmitting information. With the rapid growth of image data amount, visual compression and visual data perception are two important research topics attracting a lot…
Subsurface earth models (referred to as geo-models) are crucial for characterizing complex subsurface systems. Multiple-point statistics are commonly used to generate geo-models. In this paper, a deep-learning-based generative method is…
Generative adversarial networks (GANs) have been successfully used for considerable computer vision tasks, especially the image-to-image translation. However, generators in these networks are of complicated architectures with large number…
The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity. However, results of current approaches still fall short of their promise of high-resolution…
Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and therefore, end-to-end training is…
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core of our method is a fully parallelizable hierarchical…
In this work we introduce a differentiable version of the Compositional Pattern Producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but the weights are learned. A Lamarckian algorithm, that combines…
We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estimation. They leverage the probability product rule and a…
We introduce AutoPartGen, a model that generates objects composed of 3D parts in an autoregressive manner. This model can take as input an image of an object, 2D masks of the object's parts, or an existing 3D object, and generate a…
Inspired by the success of Convolutional Neural Networks (CNNs) for supervised prediction in images, we design the Deconvolutional Generative Model (DGM), a new probabilistic generative model whose inference calculations correspond to those…
In this paper we propose Spatial PixelCNN, a conditional autoregressive model that generates images from small patches. By conditioning on a grid of pixel coordinates and global features extracted from a Variational Autoencoder (VAE), we…