Related papers: Rethinking Resolution in the Context of Efficient …
Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well…
Recent advances in extreme image compression have revealed that mapping pixel data into highly compact latent representations can significantly improve coding efficiency. However, most existing methods compress images into 2-D latent spaces…
In recent years, attention mechanisms have been exploited in single image super-resolution (SISR), achieving impressive reconstruction results. However, these advancements are still limited by the reliance on simple training strategies and…
Low Rank Decomposition (LRD) is a model compression technique applied to the weight tensors of deep learning models in order to reduce the number of trainable parameters and computational complexity. However, due to high number of new…
2D convolution (Conv2d), which is responsible for extracting features from the input image, is one of the key modules of a convolutional neural network (CNN). However, Conv2d is vulnerable to image corruptions and adversarial samples. It is…
To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion. However, these solutions face a large drop in performance for single image queries (e.g., Image-To-Video setting).…
Fully convolutional networks (FCNs) have become de facto tool to achieve very high-level performance for many vision and non-vision tasks in general and face recognition in particular. Such high-level accuracies are normally obtained by…
We present a novel approach for super-resolution that utilizes implicit neural representation (INR) to effectively reconstruct and enhance low-resolution videos and images. By leveraging the capacity of neural networks to implicitly encode…
Hyperspectral imaging, capturing detailed spectral information for each pixel, is pivotal in diverse scientific and industrial applications. Yet, the acquisition of high-resolution (HR) hyperspectral images (HSIs) often needs to be…
The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction --…
We present a new data-driven video inpainting method for recovering missing regions of video frames. A novel deep learning architecture is proposed which contains two sub-networks: a temporal structure inference network and a spatial detail…
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing. Recently,…
Model compression is a critical area of research in deep learning, in particular in vision, driven by the need to lighten models memory or computational footprints. While numerous methods for model compression have been proposed, most focus…
Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where…
With the improvement of AI chips (e.g., GPU, TPU, and NPU) and the fast development of the Internet of Things (IoT), some robust deep neural networks (DNNs) are usually composed of millions or even hundreds of millions of parameters. Such a…
Image retrieval aims to identify visually similar images within a database using a given query image. Traditional methods typically employ both global and local features extracted from images for matching, and may also apply re-ranking…
Accurately understanding complex visual information is crucial for visual language models (VLMs). Enhancing image resolution can improve visual perception capabilities, not only reducing hallucinations but also boosting performance in tasks…
Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the…
Implicit Neural Representations (INRs) have garnered significant attention for their ability to model complex signals in various domains. Recently, INR-based frameworks have shown promise in neural video compression by embedding video…
Implicit neural representation (INR) embed various signals into neural networks. They have gained attention in recent years because of their versatility in handling diverse signal types. In the context of video, INR achieves video…