相关论文: Crosstalk Analysis of Suprime-Cam FDCCDs Using Cos…
Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on…
Object-context shortcuts remain a persistent challenge in vision-language models, undermining zero-shot reliability when test-time scenes differ from familiar training co-occurrences. We recast this issue as a causal inference problem and…
The purpose of this work is to investigate the role of the lattice in the optical Kubo sum rule in the cuprates. We compute conductivities, optical integrals W, and \Delta W between superconducting and normal states for 2-D systems with…
Cosmic microwave background data from the {\it Planck} satellite, combined with baryon acoustic oscillation measurements from the Dark Energy Spectroscopic Instrument and Type Ia supernovae from various samples, provide hints of dynamical…
The Prime Focus Spectrograph (PFS) is an optical/near-infrared multi-fiber spectrograph with 2394 science fibers, which are distributed in 1.3 degree diameter field of view at Subaru 8.2-meter telescope. The simultaneous wide wavelength…
Depth estimation from images serves as the fundamental step of 3D perception for autonomous driving and is an economical alternative to expensive depth sensors like LiDAR. The temporal photometric constraints enables self-supervised depth…
We present an approach to estimating camera rotation in crowded, real-world scenes from handheld monocular video. While camera rotation estimation is a well-studied problem, no previous methods exhibit both high accuracy and acceptable…
Light field (LF) cameras provide rich spatio-angular visual representations by sensing the visual scene from multiple perspectives and have recently emerged as a promising technology to boost the performance of human-machine systems such as…
The paper presents the third data release of Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP), a wide-field multi-band imaging survey with the Subaru 8.2m telescope. HSC-SSP has three survey layers (Wide, Deep, and UltraDeep) with…
Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching or optical flow. The application of self-supervised…
The existence of Galactic optical cirrus poses a challenge for observing faint objects within our Galaxy and dim extragalactic structures. To investigate individual cirrus filaments in the Hyper Suprime-Cam Subaru Strategic Program public…
Cameras are the defacto sensor. The growing demand for real-time and low-power computer vision, coupled with trends towards high-efficiency heterogeneous systems, has given rise to a wide range of image processing acceleration techniques at…
HiPERCAM is a high-speed camera for the study of rapid variability in the Universe. The project is funded by a 3.5MEuro European Research Council Advanced Grant. HiPERCAM builds on the success of our previous instrument, ULTRACAM, with very…
Remote sensing change captioning (RSICC) aims to describe changes between bitemporal images in natural language. Existing methods often fail under challenges like illumination differences, viewpoint changes, blur effects, leading to…
The task of image captioning aims to generate captions directly from images via the automatically learned cross-modal generator. To build a well-performing generator, existing approaches usually need a large number of described images,…
This paper presents a self-supervised feature learning method for hyperspectral image classification. Our method tries to construct two different views of the raw hyperspectral image through a cross-representation learning method. And then…
Cross-domain biometrics has been emerging as a new necessity, which poses several additional challenges, including harsh illumination changes, noise, pose variation, among others. In this paper, we explore approaches to cross-domain face…
Despite super-resolution fluorescence blinking microscopes break the diffraction limit, the intense phototoxic illumination and long-term image sequences thus far still pose to major challenges in visualizing live-organisms. Here, we…
We conduct a combined analysis to investigate dark matter (DM) with hypercharge anapole moments, focusing on scenarios where Majorana DM particles with spin 1/2, 1, 3/2, and 2 interact exclusively with Standard Model particles through…
Recent lattice measurements have given accurate estimates of the light and strange quark condensates in the proton. We use these new results to significantly improve the dark matter predictions in a set of benchmark models that represent…