Related papers: Exploiting the Signal-Leak Bias in Diffusion Model…

Diffusion models are a class of generative models that have demonstrated remarkable success in tasks such as image generation. However, one of the bottlenecks of these models is slow sampling due to the delay before the onset of trajectory…

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existing approaches rely…

Image pre-processing in the frequency domain has traditionally played a vital role in computer vision and was even part of the standard pipeline in the early days of deep learning. However, with the advent of large datasets, many…

Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…

Diffusion models generate samples by incrementally reversing a process that turns data into noise. We show that when the step size goes to zero, the reversed process is invariant to the distribution of these increments. This reveals a…

Text-to-image diffusion models have recently attracted the interest of many researchers, and inverting the diffusion process can play an important role in better understanding the generative process and how to engineer prompts in order to…

Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images from the seed noise? This is known as the…

Diffusion models for image generation often exhibit a trade-off between perceptual sample quality and data likelihood: training objectives emphasizing high-noise denoising steps yield realistic images but poor likelihoods, whereas…

Deep generative models produce data according to a learned representation, e.g. diffusion models, through a process of approximation computing possible samples. Approximation can be understood as reconstruction and the large datasets used…

Successful forensic detectors can produce excellent results in supervised learning benchmarks but struggle to transfer to real-world applications. We believe this limitation is largely due to inadequate training data quality. While most…

Searches for new astrophysical phenomena often involve several sources of non-random uncertainties which can lead to highly misleading results. Among these, model-uncertainty arising from background mismodelling can dramatically compromise…

Diffusion Probabilistic Models have demonstrated remarkable performance across a wide range of generative tasks. However, we have observed that these models often suffer from a Signal-to-Noise Ratio-timestep (SNR-t) bias. This bias refers…

Given a style-reference image as the additional image condition, text-to-image diffusion models have demonstrated impressive capabilities in generating images that possess the content of text prompts while adopting the visual style of the…

Sensor noise sources cause differences in the signal recorded across pixels in a single image and across multiple images. This paper presents a Bayesian approach to decomposing and characterizing the sensor noise sources involved in imaging…

Recent diffusion model advancements have enabled high-fidelity images to be generated using text prompts. However, a domain gap exists between generated images and real-world images, which poses a challenge in generating high-quality…

Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results,…

The reconstruction of unsteady flow fields from limited measurements is a challenging and crucial task for many engineering applications. Machine learning models are gaining popularity for solving this problem due to their ability to learn…

We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extract signals from the features of a pre-trained, frozen…

Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing de-biasing techniques rely heavily on additional training, which imposes high computational costs and risks of compromising…

One little-explored frontier of image generation and editing is the task of interpolating between two input images, a feature missing from all currently deployed image generation pipelines. We argue that such a feature can expand the…