Related papers: Edge-Aware Extended Star-Tetrix Transforms for CFA…
Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the…
We conduct a comprehensive study of the effects of incorporating galaxy morphology information in photometric redshift estimation. Using machine learning methods, we assess the changes in the scatter and catastrophic outlier fraction of…
Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently,…
Knowing the redshift of galaxies is one of the first requirements of many cosmological experiments, and as it's impossible to perform spectroscopy for every galaxy being observed, photometric redshift (photo-z) estimations are still of…
We present a new technique for detecting scattered starlight from transiting, close-orbiting extrasolar giant planets (CEGPs) that has the virtues of simplicity, robustness, linearity, and model-independence. Given a series of stellar…
This paper proposes a spatiotemporal (ST) fusion framework robust against diverse noise for satellite images, named Temporally-Similar Structure-Aware ST fusion (TSSTF). ST fusion is a promising approach to address the trade-off between the…
We present a system of X-ray photometry for the Chandra satellite. X-ray photometry can be a powerful tool to obtain flux estimates, hardness ratios, and colors unbiased by assumptions about spectral shape and independent of temporal and…
Studies of the formation and evolution of young stars and their disks rely on the knowledge of the stellar parameters of the young stars. The derivation of these parameters is commonly based on comparison with photospheric template spectra.…
The widespread use of high-definition screens in edge devices, such as end-user cameras, smartphones, and televisions, is spurring a significant demand for image enhancement. Existing enhancement models often optimize for high performance…
Purpose: The expanded encoding model incorporates spatially- and time-varying field perturbations for correction during reconstruction. So far, these reconstructions have used the conjugate gradient method with early stopping used as…
Current and upcoming generations of visible-shortwave infrared (VSWIR) imaging spectrometers promise unprecedented capacity to quantify Earth System processes across the globe. However, reliable cloud screening remains a fundamental…
Fibre-fed spectrographs now have throughputs equivalent to slit spectrographs. However, the sky subtraction accuracy that can be reached has often been pinpointed as one of the major issues associated with the use of fibres. Using technical…
We propose a novel transformer model, capable of segmenting medical images of varying modalities. Challenges posed by the fine grained nature of medical image analysis mean that the adaptation of the transformer for their analysis is still…
The Next Generation Space Telescope (NGST) will gather unprecedented spectro-photometric data on galaxies out to the highest redshifts. It is therefore crucial to identify the spectro-photometric diagnostics within reach of NGST, which will…
Medical Image-to-image translation is a key task in computer vision and generative artificial intelligence, and it is highly applicable to medical image analysis. GAN-based methods are the mainstream image translation methods, but they…
Capturing the shape and spatially-varying appearance (SVBRDF) of an object from images is a challenging task that has applications in both computer vision and graphics. Traditional optimization-based approaches often need a large number of…
Imaging through complex scattering media is severely limited by aberrations and scattering which obscure images and reduce resolution. Confocal and temporal gatings partly filter out multiple scattering but are severely degraded by…
Transformer-based 3D human pose estimation methods suffer from high computational costs due to the quadratic complexity of self-attention with respect to sequence length. Additionally, pose sequences often contain significant redundancy…
Explicit feature-grid based NeRF models have shown promising results in terms of rendering quality and significant speed-up in training. However, these methods often require a significant amount of data to represent a single scene or…
Creating accurate and efficient 3D models poses significant challenges, particularly in addressing large viewpoint variations, computational complexity, and alignment discrepancies. Efficient camera path generation can help resolve these…