Related papers: Native-Resolution Image Synthesis
This work aims to improve the applicability of diffusion models in realistic image restoration. Specifically, we enhance the diffusion model in several aspects such as network architecture, noise level, denoising steps, training image size,…
Synthetic image data generation represents a promising avenue for training deep learning models, particularly in the realm of transfer learning, where obtaining real images within a specific domain can be prohibitively expensive due to…
The recent advancement of generative foundational models has ushered in a new era of image generation in the realm of natural images, revolutionizing art design, entertainment, environment simulation, and beyond. Despite producing…
We introduce the Pyramid Diffusion Model (PDM), a novel architecture designed for ultra-high-resolution image synthesis. PDM utilizes a pyramid latent representation, providing a broader design space that enables more flexible, structured,…
Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion transformer models (DiTs). Among diffusion…
There has been tremendous progress in large-scale text-to-image synthesis driven by diffusion models enabling versatile downstream applications such as 3D object synthesis from texts, image editing, and customized generation. We present a…
Multimodal machine translation (MMT) simultaneously takes the source sentence and a relevant image as input for translation. Since there is no paired image available for the input sentence in most cases, recent studies suggest utilizing…
Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…
Currently, applying diffusion models in pixel space of high resolution images is difficult. Instead, existing approaches focus on diffusion in lower dimensional spaces (latent diffusion), or have multiple super-resolution levels of…
Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training…
Diffusion models have made significant progress in both text-to-image (T2I) generation and text-guided image editing. However, these models are typically built with billions of parameters, leading to high latency and increased deployment…
Unpaired Image-to-image Translation is a new rising and challenging vision problem that aims to learn a mapping between unaligned image pairs in diverse domains. Recent advances in this field like MUNIT and DRIT mainly focus on…
Generating realistic images is difficult, and many formulations for this task have been proposed recently. If we restrict the task to that of generating a particular class of images, however, the task becomes more tractable. That is to say,…
Currently, personalized image generation methods mostly require considerable time to finetune and often overfit the concept resulting in generated images that are similar to custom concepts but difficult to edit by prompts. We propose an…
Super-resolution reconstruction techniques entail the utilization of software algorithms to transform one or more sets of low-resolution images captured from the same scene into high-resolution images. In recent years, considerable…
Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity…
Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning…
In multimodal unsupervised image-to-image translation tasks, the goal is to translate an image from the source domain to many images in the target domain. We present a simple method that produces higher quality images than current…
We aim to leverage diffusion to address the challenging image matting task. However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles…
Flow-based Transformer models have achieved state-of-the-art image generation performance, but often suffer from high inference latency and computational cost due to their large parameter sizes. To improve inference efficiency without…