Related papers: Towards a Neural Graphics Pipeline for Controllabl…
Recent advances in deep generative models have led to an unprecedented level of realism for synthetically generated images of humans. However, one of the remaining fundamental limitations of these models is the ability to flexibly control…
Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…
In the last few years, Neural Painting (NP) techniques became capable of producing extremely realistic artworks. This paper advances the state of the art in this emerging research domain by proposing the first approach for Interactive NP.…
Neural Radiance Fields (NeRF) achieve photorealistic novel view synthesis but become costly when high-resolution (HR) rendering is required, as HR outputs demand dense sampling and higher-capacity models. Moreover, naively super-resolving…
We propose pix2pix3D, a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map, our model learns to synthesize a corresponding image from different…
This paper proposes an image-to-painting translation method that generates vivid and realistic painting artworks with controllable styles. Different from previous image-to-image translation methods that formulate the translation as…
We propose a principled convolutional neural pyramid (CNP) framework for general low-level vision and image processing tasks. It is based on the essential finding that many applications require large receptive fields for structure…
Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on…
Image generation using diffusion can be controlled in multiple ways. In this paper, we systematically analyze the equations of modern generative diffusion networks to propose a framework, called MDP, that explains the design space of…
Current text-to-image generation models often struggle to follow textual instructions, especially the ones requiring spatial reasoning. On the other hand, Large Language Models (LLMs), such as GPT-4, have shown remarkable precision in…
Current stereo-vision pipelines produce high accuracy 3D reconstruction when using multiple pairs or triplets of satellite images. However, these pipelines are sensitive to the changes between images that can occur as a result of multi-date…
Efficient rendering of photo-realistic virtual worlds is a long standing effort of computer graphics. Modern graphics techniques have succeeded in synthesizing photo-realistic images from hand-crafted scene representations. However, the…
Vector graphics are essential in design, providing artists with a versatile medium for creating resolution-independent and highly editable visual content. Recent advancements in vision-language and diffusion models have fueled interest in…
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While plenty of works extend unconditional generative models and…
Image processing is a fundamental task in computer vision, which aims at enhancing image quality and extracting essential features for subsequent vision applications. Traditionally, task-specific models are developed for individual tasks…
We propose an interactive image-manipulation system with natural language instruction, which can generate a target image from a source image and an instruction that describes the difference between the source and the target image. The…
In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo…
Controllable 3D scene generation has extensive applications in virtual reality and interior design, where the generated scenes should exhibit high levels of realism and controllability in terms of geometry. Scene graphs provide a suitable…
We present a novel method for performing flexible, 3D-aware image content manipulation while enabling high-quality novel view synthesis. While NeRF-based approaches are effective for novel view synthesis, such models memorize the radiance…
We propose a method for generating video-realistic animations of real humans under user control. In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic 3D model of…