Related papers: RGBD-GAN: Unsupervised 3D Representation Learning …
Diffusion models have shown great promise for image generation, beating GANs in terms of generation diversity, with comparable image quality. However, their application to 3D shapes has been limited to point or voxel representations that…
Generating photorealistic images of human subjects in any unseen pose have crucial applications in generating a complete appearance model of the subject. However, from a computer vision perspective, this task becomes significantly…
Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…
Real-world image manipulation has achieved fantastic progress in recent years. GAN inversion, which aims to map the real image to the latent code faithfully, is the first step in this pipeline. However, existing GAN inversion methods fail…
Diffusion models have recently become the de-facto approach for generative modeling in the 2D domain. However, extending diffusion models to 3D is challenging due to the difficulties in acquiring 3D ground truth data for training. On the…
3D-aware GANs aim to synthesize realistic 3D scenes such that they can be rendered in arbitrary perspectives to produce images. Although previous methods produce realistic images, they suffer from unstable training or degenerate solutions…
We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Different from traditional super-resolution formulation, the low-resolution…
Deep Neural Networks have recently demonstrated promising performance in binary change detection (CD) problems in remote sensing (RS), requiring a large amount of labeled multitemporal training samples. Since collecting such data is…
Generative Adversarial Networks (GANs) have emerged as powerful tools for high-quality image generation and real image editing by manipulating their latent spaces. Recent advancements in GANs include 3D-aware models such as EG3D, which…
This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs. Our method is based on generative adversarial networks…
Generative models make huge progress to the photorealistic image synthesis in recent years. To enable human to steer the image generation process and customize the output, many works explore the interpretable dimensions of the latent space…
With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due…
State-of-the-art models for high-resolution image generation, such as BigGAN and VQVAE-2, require an incredible amount of compute resources and/or time (512 TPU-v3 cores) to train, putting them out of reach for the larger research…
Deep neural networks for image quality enhancement typically need large quantities of highly-curated training data comprising pairs of low-quality images and their corresponding high-quality images. While high-quality image acquisition is…
We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-tuning an image generator, pre-trained on billions of real…
Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new…
Perceiving 3D structures from RGB images based on CAD model primitives can enable an effective, efficient 3D object-based representation of scenes. However, current approaches rely on supervision from expensive annotations of CAD models…
Generative Adversarial Networks (GAN) have demonstrated impressive results in modeling the distribution of natural images, learning latent representations that capture semantic variations in an unsupervised basis. Beyond the generation of…
Recent research has demonstrated the ability to estimate gaze on mobile devices by performing inference on the image from the phone's front-facing camera, and without requiring specialized hardware. While this offers wide potential…
Many existing conditional Generative Adversarial Networks (cGANs) are limited to conditioning on pre-defined and fixed class-level semantic labels or attributes. We propose an open set GAN architecture (OpenGAN) that is conditioned…