Related papers: Can Nano Banana 2 Replace Traditional Image Restor…

Image restoration has always been a cutting-edge topic in the academic and industrial fields of computer vision. Since degradation signals are often random and diverse, "all-in-one" models that can do blind image restoration have been…

Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na\"ive exposure of such capabilities fundamentally undermines modern…

We consider the problem of trustworthy image restoration, taking the form of a constrained optimization over the prior density. To this end, we develop generative models for the task of image super-resolution that respect the degradation…

Text-to-image models are enabling efficient design space exploration, rapidly generating images from text prompts. However, many generative AI tools are imperfect for product design applications as they are not built for the goals and…

Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I) systems, leaving image-to-image (I2I) editors underexplored. We bridge this gap with a…

Image completion has achieved significant progress due to advances in generative adversarial networks (GANs). Albeit natural-looking, the synthesized contents still lack details, especially for scenes with complex structures or images with…

Owe to the powerful generative priors, the pre-trained text-to-image (T2I) diffusion models have become increasingly popular in solving the real-world image super-resolution problem. However, as a consequence of the heavy quality…

Image restoration, which aims to retrieve and enhance degraded images, is fundamental across a wide range of applications. While conventional deep learning approaches have notably improved the image quality across various tasks, they still…

Multi-task image restoration has gained significant interest due to its inherent versatility and efficiency compared to its single-task counterpart. However, performance decline is observed with an increase in the number of tasks, primarily…

Even though it has extensively been shown that retrieval specific training of deep neural networks is beneficial for nearest neighbor image search quality, most of these models are trained and tested in the domain of landmarks images.…

Environment designers in the entertainment industry create imaginative 2D and 3D scenes for games, films, and television, requiring both fine-grained control of specific details and consistent global coherence. Designers have increasingly…

Image prior modeling is the key issue in image recovery, computational imaging, compresses sensing, and other inverse problems. Recent algorithms combining multiple effective priors such as the sparse or low-rank models, have demonstrated…

In the recent years, there has been a significant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of…

Image restoration aims to reconstruct degraded images, e.g., denoising or deblurring. Existing works focus on designing task-specific methods and there are inadequate attempts at universal methods. However, simply unifying multiple tasks…

Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…

Adaptive image restoration models can restore images with different degradation levels at inference time without the need to retrain the model. We present an approach that is highly accurate and allows a significant reduction in the number…

Due to their highly structured characteristics, faces are easier to recover than natural scenes for blind image super-resolution. Therefore, we can extract the degradation representation of an image from the low-quality and recovered face…

Generalization has long been a central challenge in real-world image restoration. While recent diffusion-based restoration methods, which leverage generative priors from text-to-image models, have made progress in recovering more realistic…

With the rapid advances of powerful multimodal models such as GPT-4o, Nano Banana, and Seedream 4.0 in Image Editing, the performance gap between closed-source and open-source models is widening, primarily due to the scarcity of…

While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to…