Related papers: DroneSR: Rethinking Few-shot Thermal Image Super-R…
Modern GANs excel at generating high quality and diverse images. However, when transferring the pretrained GANs on small target data (e.g., 10-shot), the generator tends to replicate the training samples. Several methods have been proposed…
Recently, webly supervised learning (WSL) has been studied to leverage numerous and accessible data from the Internet. Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused…
Image denoising is a fundamental and challenging task in the field of computer vision. Most supervised denoising methods learn to reconstruct clean images from noisy inputs, which have intrinsic spectral bias and tend to produce…
Recent advances in volumetric super-resolution (SR) have demonstrated strong performance in medical and scientific imaging, with transformer- and CNN-based approaches achieving impressive results even at extreme scaling factors. In this…
This paper proposes a novel framework for large-scale scene reconstruction based on 3D Gaussian splatting (3DGS) and aims to address the scalability and accuracy challenges faced by existing methods. For tackling the scalability issue, we…
Recent progress in neural rendering has brought forth pioneering methods, such as NeRF and Gaussian Splatting, which revolutionize view rendering across various domains like AR/VR, gaming, and content creation. While these methods excel at…
Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR), yet their reliance on time-consuming multi-step sampling largely hinders their practical applications. While recent efforts have…
Few-shot segmentation is a challenging task, requiring the extraction of a generalizable representation from only a few annotated samples, in order to segment novel query images. A common approach is to model each class with a single…
In the last few years, several deep learning models, especially Generative Adversarial Networks have received a lot of attention for the task of Single Image Super-Resolution (SISR). These methods focus on building an end-to-end framework,…
Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks…
A recently designed hyperspectral imaging device enables multiplexed acquisition of an entire data volume in a single snapshot thanks to monolithically-integrated spectral filters. Such an agile imaging technique comes at the cost of a…
Few-shot object detection (FSOD) aims to detect novel instances with only a limited number of labeled training samples, presenting a challenge that is particularly prominent in numerous remote sensing applications such as endangered species…
Hyperspectral super-resolution refers to the problem of fusing a hyperspectral image (HSI) and a multispectral image (MSI) to produce a super-resolution image (SRI) that has fine spatial and spectral resolution. State-of-the-art methods…
Microscopy images often suffer from high levels of noise, which can hinder further analysis and interpretation. Content-aware image restoration (CARE) methods have been proposed to address this issue, but they often require large amounts of…
State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of training set nearest…
Neural rendering has garnered substantial attention owing to its capacity for creating realistic 3D scenes. However, its applicability to extensive scenes remains challenging, with limitations in effectiveness. In this work, we propose the…
Generative neural image compression supports data representation at extremely low bitrate, synthesizing details at the client and consistently producing highly realistic images. By leveraging the similarities between quantization error and…
Recent progress on few-shot learning largely relies on annotated data for meta-learning: base classes sampled from the same domain as the novel classes. However, in many applications, collecting data for meta-learning is infeasible or…
Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation. Existing neural rendering approaches (e.g., NeRF, 3DGS) have achieved realistic reconstructions on large scenes, but optimize per…
The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…