Related papers: S^2-Transformer for Mask-Aware Hyperspectral Image…
Shortwave-infrared(SWIR) spectral information, ranging from 1 {\mu}m to 2.5{\mu}m, overcomes the limitations of traditional color cameras in acquiring scene information. However, conventional SWIR hyperspectral imaging systems face…
Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively…
Hyperspectral Images (HSIs) are crucial across numerous fields but are hindered by the long acquisition times associated with traditional spectrometers. The Coded Aperture Snapshot Spectral Imaging (CASSI) system mitigates this issue…
Self-supervised learning has demonstrated considerable potential in hyperspectral representation, yet its application in cross-domain transfer scenarios remains under-explored. Existing methods, however, still rely on source domain…
3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction.…
In recent years, hyperspectral imaging, also known as imaging spectroscopy, has been paid an increasing interest in geoscience and remote sensing community. Hyperspectral imagery is characterized by very rich spectral information, which…
Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…
Recent advances have demonstrated that coded aperture snapshot spectral imaging (CASSI) systems show great potential for capturing 3D hyperspectral images (HSIs) from a single 2D measurement. Despite the inherent spectral continuity of…
Existing learning-based hyperspectral reconstruction methods show limitations in fully exploiting the information among the hyperspectral bands. As such, we propose to investigate the chromatic inter-dependencies in their respective…
Masked reconstruction serves as a fundamental pretext task for self-supervised learning, enabling the model to enhance its feature extraction capabilities by reconstructing the masked segments from extensive unlabeled data. In human…
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…
Hyperspectral sensors capture dense spectra per pixel but suffer from low spatial resolution, causing blurred boundaries and mixed-pixel effects. Co-registered companion sensors such as multispectral, RGB, or panchromatic cameras provide…
With the rapid advancement of stereo vision technologies, stereo image compression has emerged as a crucial field that continues to draw significant attention. Previous approaches have primarily employed a unidirectional paradigm, where the…
Hyperspectral images (HSI) clustering is an important but challenging task. The state-of-the-art (SOTA) methods usually rely on superpixels, however, they do not fully utilize the spatial and spectral information in HSI 3-D structure, and…
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…
Compressive sensing (CS) reconstructs images from sub-Nyquist measurements by solving a sparsity-regularized inverse problem. Traditional CS solvers use iterative optimizers with hand crafted sparsifiers, while early data-driven methods…
Single-pixel imaging (SPI) is significant for applications constrained by transmission bandwidth or lighting band, where 3D SPI can be further realized through capturing signals carrying depth. Sampling strategy and reconstruction algorithm…
Coded aperture snapshot spectral imaging (CASSI) is a technique used to reconstruct three-dimensional hyperspectral images (HSIs) from one or several two-dimensional projection measurements. However, fewer projection measurements or more…
Unsupervised domain adaptive semantic segmentation (UDA-SS) aims to train a model on the source domain data (e.g., synthetic) and adapt the model to predict target domain data (e.g., real-world) without accessing target annotation data.…
Video snapshot compressive imaging (SCI) captures dynamic scene sequences through a two-dimensional (2D) snapshot, fundamentally relying on optical modulation for hardware compression and the corresponding software reconstruction. While…