相关论文: EMIXER: End-to-end Multimodal X-ray Generation via…

Masked generative models (MGMs) have shown impressive generative ability while providing an order of magnitude efficient sampling steps compared to continuous diffusion models. However, MGMs still underperform in image synthesis compared to…

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been…

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…

Many applications can benefit from personalized image generation models, including image enhancement, video conferences, just to name a few. Existing works achieved personalization by fine-tuning one model for each person. While being…

We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational…

In most scenarios, conditional image generation can be thought of as an inversion of the image understanding process. Since generic image understanding involves solving multiple tasks, it is natural to aim at generating images via…

Layers have become indispensable tools for professional artists, allowing them to build a hierarchical structure that enables independent control over individual visual elements. In this paper, we propose LayeringDiff, a novel pipeline for…

3D-consistent image generation from a single 2D semantic label is an important and challenging research topic in computer graphics and computer vision. Although some related works have made great progress in this field, most of the existing…

Deep metric learning aims to learn an embedding space where the distance between data reflects their class equivalence, even when their classes are unseen during training. However, the limited number of classes available in training…

Despite the surge of deep learning in the past decade, some users are skeptical to deploy these models in practice due to their black-box nature. Specifically, in the medical space where there are severe potential repercussions, we need to…

We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of applications, but the…

Recent advancements in conditional Generative Adversarial Networks (cGANs) have shown promises in label guided image synthesis. Semantic masks, such as sketches and label maps, are another intuitive and effective form of guidance in image…

As generative AI progresses rapidly, new synthetic image generators continue to emerge at a swift pace. Traditional detection methods face two main challenges in adapting to these generators: the forensic traces of synthetic images from new…

Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including…

Recently, emotional talking face generation has received considerable attention. However, existing methods only adopt one-hot coding, image, or audio as emotion conditions, thus lacking flexible control in practical applications and failing…

Generating images from semantic visual knowledge is a challenging task, that can be useful to condition the synthesis process in complex, subtle, and unambiguous ways, compared to alternatives such as class labels or text descriptions.…

Texture map production is an important part of 3D modeling and determines the rendering quality. Recently, diffusion-based methods have opened a new way for texture generation. However, restricted control flexibility and limited prompt…

This paper presents a novel method to deal with the challenging task of generating photographic images conditioned on semantic image descriptions. Our method introduces accompanying hierarchical-nested adversarial objectives inside the…

Data mixing augmentation has been widely applied to improve the generalization ability of deep neural networks. Recently, offline data mixing augmentation, e.g. handcrafted and saliency information-based mixup, has been gradually replaced…

Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and improve subsequent image processing tasks. Initial algorithms…