Related papers: Learning Latent Proxies for Controllable Single-Im…
This paper proposes a self-supervised low light image enhancement method based on deep learning. Inspired by information entropy theory and Retinex model, we proposed a maximum entropy based Retinex model. With this model, a very simple…
Recent diffusion-based one-step methods have shown remarkable progress in the field of image super-resolution, yet they remain constrained by three critical limitations: (1) inferior fidelity performance caused by the information loss from…
Stable Diffusion and ControlNet have achieved excellent results in the field of image generation and synthesis. However, due to the granularity and method of its control, the efficiency improvement is limited for professional artistic…
Diffusion models excel at image restoration via probabilistic modeling of forward noise addition and reverse denoising, and their ability to handle complex noise while preserving fine details makes them well-suited for Low-Light Image…
An image classifier may depend on incidental features stemming from a strong correlation between the feature and the classification target in the training dataset. Recently, Last Layer Retraining (LLR) with group-balanced datasets is shown…
Images captured under low-light conditions are often plagued by several challenges, including diminished contrast, increased noise, loss of fine details, and unnatural color reproduction. These factors can significantly hinder the…
Low-light image enhancement (LLIE) aims to restore natural visibility, color fidelity, and structural detail under severe illumination degradation. State-of-the-art (SOTA) LLIE techniques often rely on large models and multi-stage training,…
Relightable portrait animation aims to animate a static reference portrait to match the head movements and expressions of a driving video while adapting to user-specified or reference lighting conditions. Existing portrait animation methods…
We show how to relight a scene, depicted in a single image, such that (a) the overall shading has changed and (b) the resulting image looks like a natural image of that scene. Applications for such a procedure include generating training…
We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often…
We propose a simple, interpretable framework for solving a wide range of image reconstruction problems such as denoising and deconvolution. Given a corrupted input image, the model synthesizes a spatially varying linear filter which, when…
Retinex theory provides a principled foundation for low-light image enhancement, inspiring numerous learning-based methods that integrate its principles. However, existing methods exhibits limitations in accurately decomposing reflectance…
Light adaptation or brightness correction is a key step in improving the contrast and visual appeal of an image. There are multiple light-related tasks (for example, low-light enhancement and exposure correction) and previous studies have…
Precise, object-aware control over visual content is essential for advanced image editing and compositional generation. Yet, most existing approaches operate on entire images holistically, limiting the ability to isolate and manipulate…
In clinical CT system, the x-ray tube emits polychromatic x-rays, and the x-ray detectors operate in the current-integrating mode. This physical process is accurately described by an energy-dependent non-linear integral equation. However,…
The modern supervised approaches for human image relighting rely on training data generated from 3D human models. However, such datasets are often small (e.g., Light Stage data with a small number of individuals) or limited to diffuse…
Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios. In this paper, we develop a new…
Large-scale generative models have achieved remarkable advancements in various visual tasks, yet their application to shadow removal in images remains challenging. These models often generate diverse, realistic details without adequate…
In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our previous Self-Reference Deep Adaptive Curve Estimation (Self-DACE). To better address the…
Training deep neural networks has become a common approach for addressing image restoration problems. An alternative for training a "task-specific" network for each observation model is to use pretrained deep denoisers for imposing only the…