Related papers: Feedback Network for Mutually Boosted Stereo Image…
Self-supervised learning for depth estimation possesses several advantages over supervised learning. The benefits of no need for ground-truth depth, online fine-tuning, and better generalization with unlimited data attract researchers to…
High-resolution is a key trend in the development of synthetic aperture radar (SAR), which enables the capture of fine details and accurate representation of backscattering properties. However, traditional high-resolution SAR imaging…
Although some convolutional neural networks (CNNs) based super-resolution (SR) algorithms yield good visual performances on single images recently. Most of them focus on perfect perceptual quality but ignore specific needs of subsequent…
In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we…
Leveraging on the recent developments in convolutional neural networks (CNNs), matching dense correspondence from a stereo pair has been cast as a learning problem, with performance exceeding traditional approaches. However, it remains…
Conventional face super-resolution methods usually assume testing low-resolution (LR) images lie in the same domain as the training ones. Due to different lighting conditions and imaging hardware, domain gaps between training and testing…
Cross-modal super-resolution (SR) on real-world misaligned data is challenging, as only unlabeled low-resolution (LR) source and high-resolution (HR) guide images with complex spatial misalignment are available. Previous methods either rely…
Image super-resolution (SR) is a representative low-level vision problem. Although deep SR networks have achieved extraordinary success, we are still unaware of their working mechanisms. Specifically, whether SR networks can learn semantic…
Single-image super-resolution (SISR) networks trained with perceptual and adversarial losses provide high-contrast outputs compared to those of networks trained with distortion-oriented losses, such as L1 or L2. However, it has been shown…
We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained…
As a highly ill-posed issue, single image super-resolution (SISR) has been widely investigated in recent years. The main task of SISR is to recover the information loss caused by the degradation procedure. According to the Nyquist sampling…
Light field (LF) cameras can record scenes from multiple perspectives, and thus introduce beneficial angular information for image super-resolution (SR). However, it is challenging to incorporate angular information due to disparities among…
Face video super-resolution algorithm aims to reconstruct realistic face details through continuous input video sequences. However, existing video processing algorithms usually contain redundant parameters to guarantee different…
Currently, most low-light image enhancement methods only consider information from a single view, neglecting the correlation between cross-view information. Therefore, the enhancement results produced by these methods are often…
Fusion-based hyperspectral image (HSI) super-resolution has become increasingly prevalent for its capability to integrate high-frequency spatial information from the paired high-resolution (HR) RGB reference image. However, most of the…
Semantic segmentation for SAR (Synthetic Aperture Radar) images has attracted increasing attention in the remote sensing community recently, due to SAR's all-time and all-weather imaging capability. However, SAR images are generally more…
The cross-resolution person re-identification (CRReID) problem aims to match low-resolution (LR) query identity images against high resolution (HR) gallery images. It is a challenging and practical problem since the query images often…
Hyperspectral image (HSI) super-resolution is commonly used to overcome the hardware limitations of existing hyperspectral imaging systems on spatial resolution. It fuses a low-resolution (LR) HSI and a high-resolution (HR) conventional…
With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress. However, it remains a great challenge to accurately extract disparities from real-world image pairs taken by…
We propose Super-resolution Neural Operator (SRNO), a deep operator learning framework that can resolve high-resolution (HR) images at arbitrary scales from the low-resolution (LR) counterparts. Treating the LR-HR image pairs as continuous…