Zobrazeno 1 - 10
of 1 383
pro vyhledávání: '"Yan Zhiqiang"'
In this paper, we introduce the Selective Image Guided Network (SigNet), a novel degradation-aware framework that transforms depth completion into depth enhancement for the first time. Moving beyond direct completion using convolutional neural networ
Externí odkaz:
http://arxiv.org/abs/2412.19225
In this paper, we study the challenging problem of simultaneously removing haze and estimating depth from real monocular hazy videos. These tasks are inherently complementary: enhanced depth estimation improves dehazing via the atmospheric scattering
Externí odkaz:
http://arxiv.org/abs/2412.11395
In this paper, we introduce DCDepth, a novel framework for the long-standing monocular depth estimation task. Moving beyond conventional pixel-wise depth estimation in the spatial domain, our approach estimates the frequency coefficients of depth pat
Externí odkaz:
http://arxiv.org/abs/2410.14980
Autor:
Wirth, Henriette, Haas, Jaroslav, Šubr, Ladislav, Jerabkova, Tereza, Yan, Zhiqiang, Kroupa, Pavel
Context. The duration of star formation (SF) in globular clusters (GCs) is an essential aspect for understanding their formation. Contrary to previous presumptions that all stars above 8 M explode as core-collapse supernovae (CCSNe), recent evidence
Externí odkaz:
http://arxiv.org/abs/2410.12933
Recent RGB-guided depth super-resolution methods have achieved impressive performance under the assumption of fixed and known degradation (e.g., bicubic downsampling). However, in real-world scenarios, captured depth data often suffer from unconventi
Externí odkaz:
http://arxiv.org/abs/2410.11666
The initial mass function (IMF) is one of the most important functions in astrophysics because it is key to reconstructing the cosmological matter cycle, understanding the formation of super-massive black holes, and deciphering the light from high-re
Externí odkaz:
http://arxiv.org/abs/2410.07311
The task of vision-based 3D occupancy prediction aims to reconstruct 3D geometry and estimate its semantic classes from 2D color images, where the 2D-to-3D view transformation is an indispensable step. Most previous methods conduct forward projection
Externí odkaz:
http://arxiv.org/abs/2409.07972
Recent advances in low light image enhancement have been dominated by Retinex-based learning framework, leveraging convolutional neural networks (CNNs) and Transformers. However, the vanilla Retinex theory primarily addresses global illumination degr
Externí odkaz:
http://arxiv.org/abs/2405.16105
Autor:
Guo, Ziyi, Zhang, Zhi-Yu, Yan, Zhiqiang, Gjergo, Eda, Man, Allison, Ivison, R. J., Fu, Xiaoting, Shi, Yong
Recent observations and theories have presented a strong challenge to the universality of the stellar initial mass function (IMF) in extreme environments. A notable example has been found for starburst conditions, where evidence favours a top-heavy I
Externí odkaz:
http://arxiv.org/abs/2405.05317
Autor:
Haslbauer, Moritz, Yan, Zhiqiang, Jerabkova, Tereza, Gjergo, Eda, Kroupa, Pavel, Zonoozi, Akram Hasani
Publikováno v:
A&A 689, A221 (2024)
(Abridged) Observational estimates of galaxy properties rely on the inherent galaxy-wide initial mass function (gwIMF), which systematically varies with the global SFR and metallicity, as proposed by the integrated-galactic IMF (IGIMF) theory and sup
Externí odkaz:
http://arxiv.org/abs/2405.05313