Related papers: Moir\'eXNet: Adaptive Multi-Scale Demoir\'eing wit…

Existing denoising methods typically restore clear results by aggregating pixels from the noisy input. Instead of relying on hand-crafted aggregation schemes, we propose to explicitly learn this process with deep neural networks. We present…

In this work, we observe that model trained on vast general images via masking strategy, has been naturally embedded with their distribution knowledge, thus spontaneously attains the underlying potential for strong image denoising. Based on…

The remastering of vintage film comprises of a diversity of sub-tasks including super-resolution, noise removal, and contrast enhancement which aim to restore the deteriorated film medium to its original state. Additionally, due to the…

Image super-resolution (SR) is an underdetermined inverse problem, where a large number of plausible high-resolution images can explain the same downsampled image. Most current single image SR methods use empirical risk minimisation, often…

In this paper, we introduce DiffusionMat, a novel image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. Diverging from conventional methods that utilize trimaps merely as loose…

Precise boundary annotations of image regions can be crucial for downstream applications which rely on region-class semantics. Some document collections contain densely laid out, highly irregular and overlapping multi-class region instances…

Prompt learning is a dominant paradigm for adapting pre-trained Vision-Language Models (VLMs) to downstream tasks. However, existing methods often rely on a simplistic, layer-centric view, assuming shallow layers capture general features…

With the rapid advancement of mobile imaging, capturing screens using smartphones has become a prevalent practice in distance learning and conference recording. However, moir\'e artifacts, caused by frequency aliasing between display…

Mask-guided matting networks have achieved significant improvements and have shown great potential in practical applications in recent years. However, simply learning matting representation from synthetic and lack-of-real-world-diversity…

Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze,…

We present a compartmentalized approach to finding the maximum a-posteriori (MAP) estimate of a latent time series that obeys a dynamic stochastic model and is observed through noisy measurements. We specifically consider modern signal…

Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations are either…

Degradation-agnostic image restoration aims to handle diverse corruptions with one unified model, but faces fundamental challenges in balancing efficiency and performance across different degradation types. Existing approaches either…

Infrared and visible image fusion aims to integrate complementary multi-modal information into a single fused result. However, existing methods 1) fail to account for the degradation visible images under adverse weather conditions, thereby…

As pretrained models are increasingly shared on the web, ensuring that models can forget or delete sensitive, copyrighted, or private information upon request has become crucial. Machine unlearning has been proposed to address this…

Many imaging science tasks can be modeled as a discrete linear inverse problem. Solving linear inverse problems is often challenging, with ill-conditioned operators and potentially non-unique solutions. Embedding prior knowledge, such as…

CNNs and Self attention have achieved great success in multimedia applications for dynamic association learning of self-attention and convolution in image restoration. However, CNNs have at least two shortcomings: 1) limited receptive…

Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and these methods can restore an image by exploiting information…

In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize to challenging…

In this paper, we explore a new generative approach for learning visual representations. Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We find that training with Mean Squared Error (MSE)…