Related papers: Simple Baselines for Image Restoration

Nowadays deep learning-based methods have achieved a remarkable progress at the image classification task among a wide range of commonly used datasets (ImageNet, CIFAR, SVHN, Caltech 101, SUN397, etc.). SOTA performance on each of the…

Current methods for restoring underexposed images typically rely on supervised learning with paired underexposed and well-illuminated images. However, collecting such datasets is often impractical in real-world scenarios. Moreover, these…

Integer-arithmetic-only networks have been demonstrated effective to reduce computational cost and to ensure cross-platform consistency. However, previous works usually report a decline in the inference accuracy when converting well-trained…

In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images,…

Image enhancement is a critical task in computer vision and photography that is often entangled with noise. This renders the traditional Image Signal Processing (ISP) ineffective compared to the advances in deep learning. However, the…

All-in-one image restoration aims to handle diverse degradations (e.g., noise, blur, adverse weather) within a unified framework, yet existing methods increasingly rely on complex architectures (e.g., Mixture-of-Experts, diffusion models)…

Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance. This paper presents a novel SurroundNet…

Deep convolutional neural networks perform better on images containing spatially invariant degradations, also known as synthetic degradations; however, their performance is limited on real-degraded photographs and requires multiple-stage…

Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the…

Lensless cameras based on thin diffusers offer a compact alternative to conventional refractive imaging but rely on computational reconstruction, since the diffuser's point spread function (PSF) globally multiplexes every scene point across…

Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the…

Two difficulties here make low-light image enhancement a challenging task; firstly, it needs to consider not only luminance restoration but also image contrast, image denoising and color distortion issues simultaneously. Second, the…

In this paper we analyze and compare approaches for 3D reconstruction from low-resolution (250x250), high radial distortion stereo images, which are acquired with small baseline (approximately 1mm). These images are acquired with the system…

Existing studies tend tofocus onmodel modifications and integration with higher accuracy, which improve performance but also carry huge computational costs, resulting in longer detection times. Inmedical imaging, the use of time is…

Following their success in visual recognition tasks, Vision Transformers(ViTs) are being increasingly employed for image restoration. As a few recent works claim that ViTs for image classification also have better robustness properties, we…

Image processing is both one of the most exciting domains for applying artificial intelligence and the most computationally expensive. Nanostructured metasurfaces have opened the door to the ultimate energy saving by directly processing…

Natural images tend to mostly consist of smooth regions with individual pixels having highly correlated spectra. This information can be exploited to recover hyperspectral images of natural scenes from their incomplete and noisy…

This paper presents our solution to the NTIRE 2026 Image Denoising Challenge (Gaussian color image denoising at fixed noise level $\sigma = 50$). Rather than proposing a new restoration backbone, we revisit the performance boundary of the…

Recent research has explored complex loss functions for deblurring. In this work, we explore the impact of a previously introduced loss function - Q which explicitly addresses sharpness and employ it to fine-tune State-of-the-Art (SOTA)…

State-of-the-art (SOTA) video denoising methods employ multi-frame simultaneous denoising mechanisms, resulting in significant delays (e.g., 16 frames), making them impractical for real-time cameras. To overcome this limitation, we propose…