相关论文: Rainbow: a colorful approach on multi-passband lig…
Joint RGB-infrared perception is essential for achieving robustness under diverse weather and illumination conditions. Although foundation models excel within single modalities, they suffer from substantial cross-modal degradation, an issue…
We developed a deeP architecturE for the LIght Curve ANalysis (PELICAN) for the characterization and the classification of light curves. It takes light curves as input, without any additional features. PELICAN can deal with the sparsity and…
Modern machine learning models use an ever-increasing number of parameters to train (175 billion parameters for GPT-3) with large datasets to obtain better performance. Bigger is better has been the norm. Optical computing has been…
We tackle the problem of estimating flow between two images with large lighting variations. Recent learning-based flow estimation frameworks have shown remarkable performance on image pairs with small displacement and constant…
Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hence, the resilience of models to such real-world…
We propose a method to detect and reconstruct multiple 3D objects from a single RGB image. The key idea is to optimize for detection, alignment and shape jointly over all objects in the RGB image, while focusing on realistic and physically…
Photometry is the most easily acquired information about supernovae. The light curves constructed from regular imaging provide signatures not only for the energy input, the radiation escape, the local environment and the progenitor stars,…
We present a new multiband extension to the crowdsource photometric pipeline, enabling simultaneous fitting across multiple imaging bands in crowded fields. The core idea is that multiple images of the same part of the sky should have the…
Rainbow connection number, rc(G), of a connected graph G is the minimum number of colors needed to color its edges so that every pair of vertices is connected by at least one path in which no two edges are colored the same (Note that the…
This paper deals with a challenging, frequently encountered, yet not properly investigated problem in two-frame optical flow estimation. That is, the input frames are compounds of two imaging layers -- one desired background layer of the…
Compared to RGB images, raw sensor data provides a richer representation of information, which is crucial for accurate recognition, particularly under challenging conditions such as low-light environments. The traditional Image Signal…
This paper presents a novel and efficient image enhancement method based on pigment representation. Unlike conventional methods where the color transformation is restricted to pre-defined color spaces like RGB, our method dynamically adapts…
Targeted color-dots with varying shapes and sizes in images are first exhaustively identified, and then their multiscale 2D geometric patterns are extracted for testing spatial uniformness in a progressive fashion. Based on color theory in…
Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent…
Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo. This simulated data does not model many of the important…
We propose a simple, interpretable framework for solving a wide range of image reconstruction problems such as denoising and deconvolution. Given a corrupted input image, the model synthesizes a spatially varying linear filter which, when…
Intensive reverberation mapping monitoring programs combine ground-based photometric observations from different telescopes, requiring intercalibration of lightcurves to reduce systematic instrumental differences. We present a new iterative…
We present a rigorous mathematical solution to photometric redshift estimation and the more general inversion problem. The challenge we address is to meaningfully constrain unknown properties of astronomical sources based on given…
High energy dual-energy X-ray Digital Radiography(DR) imaging is mainly used in material recognition of the cargo inspection. We introduce the development history and the principle of the technology and describe the data process flow of our…
Reconfigurable intelligent surface (RIS) is considered to be an energy-efficient approach to reshape the wireless environment for improved throughput. Its passive feature greatly reduces the energy consumption, which makes RIS a promising…