Related papers: Dual Diffusion Architecture for Fisheye Image Rect…

Diffusion bridge models establish probabilistic paths between arbitrary paired distributions and exhibit great potential for universal image restoration. Most existing methods merely treat them as simple variants of stochastic interpolants,…

In this work, we present Blind-Spot Guided Diffusion, a novel self-supervised framework for real-world image denoising. Our approach addresses two major challenges: the limitations of blind-spot networks (BSNs), which often sacrifice local…

The accuracy of face recognition systems has improved significantly in the past few years, thanks to the large amount of data collected and advancements in neural network architectures. However, these large-scale datasets are often…

Ultrasound computed tomography (USCT) holds great promise for breast cancer screening. Waveform inversion-based image reconstruction methods account for higher order diffraction effects and can produce high-resolution USCT images, but are…

We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training…

Visual recognition models are prone to learning spurious correlations induced by a biased training set where certain conditions $B$ (\eg, Indoors) are over-represented in certain classes $Y$ (\eg, Big Dogs). Synthetic data from…

Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis, image restoration (IR) has a strong constraint to…

Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Current mainstream DA strategies are synthetic-based methods,…

In video surveillance as well as automotive applications, so-called fisheye cameras are often employed to capture a very wide angle of view. As such cameras depend on projections quite different from the classical perspective projection,…

This paper introduces a novel approach to leverage the generalizability of Diffusion Models for Source-Free Domain Adaptation (DM-SFDA). Our proposed DMSFDA method involves fine-tuning a pre-trained text-to-image diffusion model to generate…

Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and…

Existing image restoration methods mostly leverage the posterior distribution of natural images. However, they often assume known degradation and also require supervised training, which restricts their adaptation to complex real…

Blind image separation (BIS) refers to the inverse problem of simultaneously estimating and restoring multiple independent source images from a single observation image under conditions of unknown mixing mode and without prior knowledge of…

Exposure correction is one of the fundamental tasks in image processing and computational photography. While various methods have been proposed, they either fail to produce visually pleasing results, or only work well for limited types of…

Robot manipulation in the real world is fundamentally constrained by the visual sim2real gap, where depth observations collected in simulation fail to reflect the complex noise patterns inherent to real sensors. In this work, inspired by…

Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and climate science. In practice, filtering methods rely on…

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as…

Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without…

Underwater image restoration is a challenging task because of water effects that increase dramatically with distance. This is worsened by lack of ground truth data of clean scenes without water. Diffusion priors have emerged as strong image…

Blind face restoration (BFR) is important while challenging. Prior works prefer to exploit GAN-based frameworks to tackle this task due to the balance of quality and efficiency. However, these methods suffer from poor stability and…