Related papers: Towards Application Aligned Synthetic Surgical Ima…

The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…

Large generative diffusion models have revolutionized text-to-image generation and offer immense potential for conditional generation tasks such as image enhancement, restoration, editing, and compositing. However, their widespread adoption…

Although computer-aided diagnosis (CADx) and detection (CADe) systems have made significant progress in various medical domains, their application is still limited in specialized fields such as otorhinolaryngology. In the latter, current…

We propose SymDiff, a method for constructing equivariant diffusion models using the framework of stochastic symmetrisation. SymDiff resembles a learned data augmentation that is deployed at sampling time, and is lightweight,…

Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through…

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50% to 80%) is used for training and the rest for validation. In many problems, however, the data is highly imbalanced in regard to different…

Deep learning-based food image classification enables precise identification of food categories, further facilitating accurate nutritional analysis. However, real-world food images often show a skewed distribution, with some food types…

In this paper, we propose SRIF, a novel Semantic shape Registration framework based on diffusion-based Image morphing and Flow estimation. More concretely, given a pair of extrinsically aligned shapes, we first render them from multi-views,…

Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to…

Current deep learning approaches for prostate cancer lesion segmentation achieve limited performance, with Dice scores of 0.32 or lower in large patient cohorts. To address this limitation, we investigate synthetic correlated diffusion…

We address hyperspectral image (HSI) synthesis, a problem that has garnered growing interest yet remains constrained by the conditional generative paradigms that limit sample diversity. While diffusion models have emerged as a…

Diffusion models have shown impressive results in generating high-quality conditional samples using guidance techniques such as Classifier-Free Guidance (CFG). However, existing methods often require additional training or neural function…

This paper presents a novel unsupervised domain adaptation framework, called Synergistic Image and Feature Adaptation (SIFA), to effectively tackle the problem of domain shift. Domain adaptation has become an important and hot topic in…

Magnetic Resonance Imaging (MRI) produces excellent soft tissue contrast, albeit it is an inherently slow imaging modality. Promising deep learning methods have recently been proposed to reconstruct accelerated MRI scans. However, existing…

By leveraging the text-to-image diffusion priors, score distillation can synthesize 3D contents without paired text-3D training data. Instead of spending hours of online optimization per text prompt, recent studies have been focused on…

Pseudo-healthy image inpainting is an essential preprocessing step for analyzing pathological brain MRI scans. Most current inpainting methods favor slice-wise 2D models for their high in-plane fidelity, but their independence across slices…

Recently, diffusion-based blind super-resolution (SR) methods have shown great ability to generate high-resolution images with abundant high-frequency detail, but the detail is often achieved at the expense of fidelity. Meanwhile, another…

Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. However, these approaches typically require tens or even hundreds of…

We propose SparseFusion, a sparse view 3D reconstruction approach that unifies recent advances in neural rendering and probabilistic image generation. Existing approaches typically build on neural rendering with re-projected features but…

Accurate instrument segmentation in endoscopic vision of robot-assisted surgery is challenging due to reflection on the instruments and frequent contacts with tissue. Deep neural networks (DNN) show competitive performance and are in favor…