Related papers: FCVSR: A Frequency-aware Method for Compressed Vid…
Videos typically record the streaming and continuous visual data as discrete consecutive frames. Since the storage cost is expensive for videos of high fidelity, most of them are stored in a relatively low resolution and frame rate. Recent…
Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities. Although many deep learning-based VSR…
Reference-based image super-resolution (RefSR) is a promising SR branch and has shown great potential in overcoming the limitations of single image super-resolution. While previous state-of-the-art RefSR methods mainly focus on improving…
In this paper, we propose a novel video super-resolution method that aims at generating high-fidelity high-resolution (HR) videos from low-resolution (LR) ones. Previous methods predominantly leverage temporal neighbor frames to assist the…
While single-image super-resolution (SISR) has attracted substantial interest in recent years, the proposed approaches are limited to learning image priors in order to add high frequency details. In contrast, multi-frame super-resolution…
Wide area surveillance has many applications and tracking of objects under observation is an important task, which often needs high spatio-temporal resolution (HSTR) video for better precision. This paper presents the usage of multiple…
The past few years have witnessed great success in applying deep learning to enhance the quality of compressed image/video. The existing approaches mainly focus on enhancing the quality of a single frame, ignoring the similarity between…
Perceptual image super-resolution (SR) methods restore degraded images and produce sharp outputs. In practice, those outputs are usually recompressed for storage and transmission. Ignoring recompression is suboptimal as the downstream codec…
Due to the limitations of capture devices and scenarios, egocentric videos frequently have low visual quality, mainly caused by high compression and severe motion blur. With the increasing application of egocentric videos, there is an…
Audio super-resolution aims to recover missing high-frequency details from bandwidth-limited low-resolution audio, thereby improving the naturalness and perceptual quality of the reconstructed signal. However, most existing methods directly…
Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling. We propose…
Although CNN has reached satisfactory performance in image-related tasks, using CNN to process videos is much more challenging due to the enormous size of raw video streams. In this work, we propose to use motion vectors and residuals from…
A Recurrent Neural Network (RNN) for Video Super Resolution (VSR) is generally trained with randomly clipped and cropped short videos extracted from original training videos due to various challenges in learning RNNs. However, since this…
Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate super-resolved videos with higher resolution(HR) and higher frame rate (HFR). Quite intuitively, pioneering two-stage based methods complete ST-VSR by directly combining two…
The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. Current Video Super-Resolution methods are not robust to mismatch between…
Image signals typically are defined on a rectangular two-dimensional grid. However, there exist scenarios where this is not fulfilled and where the image information only is available for a non-regular subset of pixel position. For…
Video super-resolution (SR) aims at generating a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The key challenge for video SR lies in the effective…
In video super-resolution, the spatio-temporal coherence between, and among the frames must be exploited appropriately for accurate prediction of the high resolution frames. Although 2D convolutional neural networks (CNNs) are powerful in…
Diffusion models have significantly advanced video super-resolution (VSR) by enhancing perceptual quality, largely through elaborately designed temporal modeling to ensure inter-frame consistency. However, existing methods usually suffer…
Recently, Vision Transformer has achieved great success in recovering missing details in low-resolution sequences, i.e., the video super-resolution (VSR) task. Despite its superiority in VSR accuracy, the heavy computational burden as well…