Related papers: Unsupervised Generative 3D Shape Learning from Nat…

We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In…

Deep learning based pan-sharpening has received significant research interest in recent years. Most of existing methods fall into the supervised learning framework in which they down-sample the multi-spectral (MS) and panchromatic (PAN)…

We introduce a novel framework to build a model that can learn how to segment objects from a collection of images without any human annotation. Our method builds on the observation that the location of object segments can be perturbed…

As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect…

Existing generative models for 3D shapes are typically trained on a large 3D dataset, often of a specific object category. In this paper, we investigate the deep generative model that learns from only a single reference 3D shape.…

Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new…

This paper presents a "learning to learn" approach to figure-ground image segmentation. By exploring webly-abundant images of specific visual effects, our method can effectively learn the visual-effect internal representations in an…

Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time limits the deployment in real scenarios. This work aims at…

Fully unsupervised 3D representation learning has gained attention owing to its advantages in data collection. A successful approach involves a viewpoint-aware approach that learns an image distribution based on generative models (e.g.,…

As a classic statistical model of 3D facial shape and albedo, 3D Morphable Model (3DMM) is widely used in facial analysis, e.g., model fitting, image synthesis. Conventional 3DMM is learned from a set of 3D face scans with associated…

Generating accurate 3D models is a challenging problem that traditionally requires explicit learning from 3D datasets using supervised learning. Although recent advances have shown promise in learning 3D models from 2D images, these methods…

In this paper, we present an end-to-end learning framework for detailed 3D face reconstruction from a single image. Our approach uses a 3DMM-based coarse model and a displacement map in UV-space to represent a 3D face. Unlike previous work…

In this paper, we address unsupervised pose-guided person image generation, which is known challenging due to non-rigid deformation. Unlike previous methods learning a rock-hard direct mapping between human bodies, we propose a new pathway…

3D shape models are naturally parameterized using vertices and faces, \ie, composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generative tasks using convolutional neural networks focus on a…

We introduce a new problem of generating an image based on a small number of key local patches without any geometric prior. In this work, key local patches are defined as informative regions of the target object or scene. This is a…

3D shape generation is a challenging problem due to the high-dimensional output space and complex part configurations of real-world objects. As a result, existing algorithms experience difficulties in accurate generative modeling of 3D…

This paper presents a method to reconstruct high-quality textured 3D models from both multi-view and single-view images. The reconstruction is posed as an adaptation problem and is done progressively where in the first stage, we focus on…

There have been a fairly of research interests in exploring the disentanglement of appearance and shape from human images. Most existing endeavours pursuit this goal by either using training images with annotations or regulating the…

Learning sensorimotor control policies from high-dimensional images crucially relies on the quality of the underlying visual representations. Prior works show that structured latent space such as visual keypoints often outperforms…

We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the…