Related papers: Hierarchical Separable Video Transformer for Snaps…
Video snapshot compressive imaging (SCI) captures multiple sequential video frames by a single measurement using the idea of computational imaging. The underlying principle is to modulate high-speed frames through different masks and these…
Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…
Snapshot compressive imaging (SCI) encodes high-speed scene video into a snapshot measurement and then computationally makes reconstructions, allowing for efficient high-dimensional data acquisition. Numerous algorithms, ranging from…
This paper presents a novel framework called HST for semi-supervised video object segmentation (VOS). HST extracts image and video features using the latest Swin Transformer and Video Swin Transformer to inherit their inductive bias for the…
Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target…
We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale…
To capture high-speed videos using a two-dimensional detector, video snapshot compressive imaging (SCI) is a promising system, where the video frames are coded by different masks and then compressed to a snapshot measurement. Following…
Recently, Spectral Compressive Imaging (SCI) has achieved remarkable success, unlocking significant potential for dynamic spectral vision. However, existing reconstruction methods, primarily image-based, suffer from two limitations: (i)…
Video snapshot compressive imaging (SCI) uses a two-dimensional detector to capture consecutive video frames during a single exposure time. Following this, an efficient reconstruction algorithm needs to be designed to reconstruct the…
Conventional image sensors have limited dynamic range, causing saturation in high-dynamic-range (HDR) scenes. Modulo cameras address this by folding incident irradiance into a bounded range, yet require specialized unwrapping algorithms to…
Deep network-based image and video Compressive Sensing(CS) has attracted increasing attentions in recent years. However, in the existing deep network-based CS methods, a simple stacked convolutional network is usually adopted, which not…
Computational spectral imaging (CSI) achieves real-time hyperspectral imaging through co-designed optics and algorithms, but typical CSI methods suffer from a bulky footprint and limited fidelity. Therefore, Spectral Deconvolution imaging…
Hyperspectral imaging (HSI) is essential across various disciplines for its capacity to capture rich spectral information. However, efficiently reconstructing hyperspectral images from compressive sensing measurements presents significant…
Recent advancements in learned image compression (LIC) methods have demonstrated superior performance over traditional hand-crafted codecs. These learning-based methods often employ convolutional neural networks (CNNs) or Transformer-based…
Snapshot compressive imaging (SCI) refers to compressive imaging systems where multiple frames are mapped into a single measurement, with video compressive imaging and hyperspectral compressive imaging as two representative applications.…
Modeling hyperspectral imagery (HSI) across different sensors presents a fundamental challenge due to variations in wavelength coverage, band sampling, and channel dimensionality. As a result, models trained under a fixed spectral…
We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main…
Video inpainting aims to fill the given spatiotemporal holes with realistic appearance but is still a challenging task even with prosperous deep learning approaches. Recent works introduce the promising Transformer architecture into deep…
Event-based object detection has gained increasing attention due to its advantages such as high temporal resolution, wide dynamic range, and asynchronous address-event representation. Leveraging these advantages, Spiking Neural Networks…
Many algorithms have been developed to solve the inverse problem of coded aperture snapshot spectral imaging (CASSI), i.e., recovering the 3D hyperspectral images (HSIs) from a 2D compressive measurement. In recent years, learning-based…