Related papers: Learning Spatiotemporal Frequency-Transformer for …
Spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency. This approach encodes a lower resolution version of the input video and reconstructs the original resolution…
Impressive results on real-world image super-resolution (Real-ISR) have been achieved by employing pre-trained stable diffusion (SD) models. However, one critical issue of such methods lies in their poor reconstruction of image fine…
In the blind single image super-resolution (SISR) task, existing works have been successful in restoring image-level unknown degradations. However, when a single video frame becomes the input, these works usually fail to address…
In recent years, deep learning has made great progress in many fields such as image recognition, natural language processing, speech recognition and video super-resolution. In this survey, we comprehensively investigate 33 state-of-the-art…
Recent advancements in deep learning techniques have significantly improved the quality of compressed videos. However, previous approaches have not fully exploited the motion characteristics of compressed videos, such as the drastic change…
Video object segmentation is a fundamental research problem in computer vision. Recent techniques have often applied attention mechanism to object representation learning from video sequences. However, due to temporal changes in the video…
Speech super-resolution (SR) reconstructs high-fidelity wideband speech from low-resolution inputs-a task that necessitates reconciling global harmonic coherence with local transient sharpness. While diffusion-based generative models yield…
Video super-resolution, which attempts to reconstruct high-resolution video frames from their corresponding low-resolution versions, has received increasingly more attention in recent years. Most existing approaches opt to use deformable…
Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…
In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i.e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence. The existing approaches to RefVSR…
Video super-resolution (VSR) has many applications that pose strict causal, real-time, and latency constraints, including video streaming and TV. We address the VSR problem under these settings, which poses additional important challenges…
As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscaling has become a new trend in the modern video delivery…
Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400)…
Video dimensions are continuously increasing to provide more realistic and immersive experiences to global streaming and social media viewers. However, increments in video parameters such as spatial resolution and frame rate are inevitably…
Content-based video retrieval aims to find videos from a large video database that are similar to or even near-duplicate of a given query video. Video representation and similarity search algorithms are crucial to any video retrieval…
Learning based video compression attracts increasing attention in the past few years. The previous hybrid coding approaches rely on pixel space operations to reduce spatial and temporal redundancy, which may suffer from inaccurate motion…
3D super-resolution aims to reconstruct high-fidelity 3D models from low-resolution (LR) multi-view images. Early studies primarily focused on single-image super-resolution (SISR) models to upsample LR images into high-resolution images.…
Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occlusion in dense clusters, and complex background interference. To address these issues, this paper proposes FSDETR, a…
Recent video super-resolution (VSR) approaches use deep neural networks to enhance low-quality input videos and recover visual detail, with diffusion-based methods in particular showing promising results. In this paper, we investigate…
The effective utilization of observational data is frequently hindered by insufficient resolution. To address this problem, we present a new spatio-temporal super-resolution (STSR) model, called InWaveSR. It is built on a deep learning…