Related papers: M6-UFC: Unifying Multi-Modal Controls for Conditio…
We offer a method for one-shot mask-guided image synthesis that allows controlling manipulations of a single image by inverting a quasi-robust classifier equipped with strong regularizers. Our proposed method, entitled MAGIC, leverages…
In this paper, we propose a novel variational generator framework for conditional GANs to catch semantic details for improving the generation quality and diversity. Traditional generators in conditional GANs simply concatenate the…
Automatic thin-prep cytologic test (TCT) screening can assist pathologists in finding cervical abnormality towards accurate and efficient cervical cancer diagnosis. Current automatic TCT screening systems mostly involve abnormal cervical…
Urban morphology is fundamental to determining urban functionality and vitality. Prevailing simulation methods, however, often oversimplify morphological generation as a geometric problem, lacking a profound understanding of urban semantics…
Fine-grained control of text-to-image diffusion transformer models (DiT) remains a critical challenge for practical deployment. While recent advances such as OminiControl and others have enabled a controllable generation of diverse control…
We introduce the Multi-Instance Generation (MIG) task, which focuses on generating multiple instances within a single image, each accurately placed at predefined positions with attributes such as category, color, and shape, strictly…
Numerous task-specific variants of conditional generative adversarial networks have been developed for image completion. Yet, a serious limitation remains that all existing algorithms tend to fail when handling large-scale missing regions.…
Generating 3D images of complex objects conditionally from a few 2D views is a difficult synthesis problem, compounded by issues such as domain gap and geometric misalignment. For instance, a unified framework such as Generative Adversarial…
Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire. This paper describes Diffusion-Decoding models with Contrastive representations…
The Latent Diffusion Model (LDM) has demonstrated strong capabilities in high-resolution image generation and has been widely employed for Pose-Guided Person Image Synthesis (PGPIS), yielding promising results. However, the compression…
We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typically hand-craft geometric transformations, we learn…
We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear…
We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing diffusion-based editing methods often struggle to maintain…
The introduction of high-quality image generation models, particularly the StyleGAN family, provides a powerful tool to synthesize and manipulate images. However, existing models are built upon high-quality (HQ) data as desired outputs,…
Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sensitive areas such as medical imaging. Medical images feature…
In recent years, diffusion models have gained popularity for their ability to generate higher-quality images in comparison to GAN models. However, like any other large generative models, these models require a huge amount of data,…
Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and…
We present a Multi-Instance Generation (MIG) task, simultaneously generating multiple instances with diverse controls in one image. Given a set of predefined coordinates and their corresponding descriptions, the task is to ensure that…
We present an approach to synthesizing photographic images conditioned on semantic layouts. Given a semantic label map, our approach produces an image with photographic appearance that conforms to the input layout. The approach thus…
Synthesizing MR imaging sequences is highly relevant in clinical practice, as single sequences are often missing or are of poor quality (e.g. due to motion). Naturally, the idea arises that a target modality would benefit from multi-modal…