Related papers: DIAMOND: Directed Inference for Artifact Mitigatio…

World models constitute a promising approach for training reinforcement learning agents in a safe and sample-efficient manner. Recent world models predominantly operate on sequences of discrete latent variables to model environment…

During the process of computed tomography (CT), metallic implants often cause disruptive artifacts in the reconstructed images, impeding accurate diagnosis. Several supervised deep learning-based approaches have been proposed for reducing…

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Virtual try-on (VITON) aims to generate realistic images of a person wearing a target garment, requiring precise garment alignment in try-on regions and faithful preservation of identity and background in non-try-on regions. While latent…

Motion artifacts remain a significant challenge in Magnetic Resonance Imaging (MRI), compromising diagnostic quality and potentially leading to misdiagnosis or repeated scans. Existing deep learning approaches for motion artifact correction…

Metal artifacts from high-attenuation implants severely degrade CT image quality, obscuring critical anatomical structures and posing a challenge for standard deep learning methods that require extensive paired training data. We propose a…

Ancient artifacts are an important medium for cultural preservation and restoration. However, many physical copies of artifacts are either damaged or lost, leaving a blank space in archaeological and historical studies that calls for…

Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature. The users, however, may face litigation risks owing to the models'…

Aligning diffusion models with user preferences has been a key challenge. Existing methods for aligning diffusion models either require retraining or are limited to differentiable reward functions. To address these limitations, we propose a…

Image restoration is a typical ill-posed problem, and it contains various tasks. In the medical imaging field, an ill-posed image interrupts diagnosis and even following image processing. Both traditional iterative and up-to-date deep…

Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment…

Decentralized bilevel optimization has received increasing attention recently due to its foundational role in many emerging multi-agent learning paradigms (e.g., multi-agent meta-learning and multi-agent reinforcement learning) over…

Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost and the challenge of teaching models the abstract concept of…

In medical imaging, the diffusion models have shown great potential for synthetic image generation tasks. However, these approaches often lack the interpretable connections between the generated and real images and can create anatomically…

Recent advancements in diffusion and flow-matching models have demonstrated remarkable capabilities in high-fidelity image synthesis. A prominent line of research involves reward-guided guidance, which steers the generation process during…

Subject-driven text-to-image generation has witnessed remarkable advancements in its ability to learn and capture characteristics of a subject using only a limited number of images. However, existing methods commonly rely on high-quality…

The success of deep learning in computer vision over the past decade has hinged on large labeled datasets and strong pretrained models. In data-scarce settings, the quality of these pretrained models becomes crucial for effective transfer…

In spite of recent progress, image diffusion models still produce artifacts. A common solution is to leverage the feedback provided by quality assessment systems or human annotators to optimize the model, where images are generally rated in…

Recent generative models show impressive results in photo-realistic image generation. However, artifacts often inevitably appear in the generated results, leading to downgraded user experience and reduced performance in downstream tasks.…