Zobrazeno 1 - 10
of 392
pro vyhledávání: '"Zhang, Yulun"'
Autor:
Qian, Cheng, Zhang, Yulun, Bhatt, Varun, Fontaine, Matthew Christopher, Nikolaidis, Stefanos, Li, Jiaoyang
We use the Quality Diversity (QD) algorithm with Neural Cellular Automata (NCA) to generate benchmark maps for Multi-Agent Path Finding (MAPF) algorithms. Previously, MAPF algorithms are tested using fixed, human-designed benchmark maps. However, suc
Externí odkaz:
http://arxiv.org/abs/2409.06888
Transformers have achieved the state-of-the-art performance on solving the inverse problem of Snapshot Compressive Imaging (SCI) for video, whose ill-posedness is rooted in the mixed degradation of spatial masking and temporal aliasing. However, prev
Externí odkaz:
http://arxiv.org/abs/2407.11946
Two-view pose estimation is essential for map-free visual relocalization and object pose tracking tasks. However, traditional matching methods suffer from time-consuming robust estimators, while deep learning-based pose regressors only cater to camer
Externí odkaz:
http://arxiv.org/abs/2407.08199
Transformers have exhibited promising performance in computer vision tasks including image super-resolution (SR). However, popular transformer-based SR methods often employ window self-attention with quadratic computational complexity to window sizes
Externí odkaz:
http://arxiv.org/abs/2407.05878
Autor:
He, Chunming, Shen, Yuqi, Fang, Chengyu, Xiao, Fengyang, Tang, Longxiang, Zhang, Yulun, Zuo, Wangmeng, Guo, Zhenhua, Li, Xiu
Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising process, have
Externí odkaz:
http://arxiv.org/abs/2406.11138
Autor:
Fang, Chengyu, He, Chunming, Xiao, Fengyang, Zhang, Yulun, Tang, Longxiang, Zhang, Yuelin, Li, Kai, Li, Xiu
Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To add
Externí odkaz:
http://arxiv.org/abs/2406.07966
Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit parameters and efficient integer/bitwise constructions for storage compression
Externí odkaz:
http://arxiv.org/abs/2406.06649
Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating
Externí odkaz:
http://arxiv.org/abs/2406.05723
Autor:
Dong, Jiahua, Yin, Hui, Li, Hongliu, Li, Wenbo, Zhang, Yulun, Khan, Salman, Khan, Fahad Shahbaz
Deep unfolding methods have made impressive progress in restoring 3D hyperspectral images (HSIs) from 2D measurements through convolution neural networks or Transformers in spectral compressive imaging. However, they cannot efficiently capture long-r
Externí odkaz:
http://arxiv.org/abs/2406.00449
Reconstructing missing details from degraded low-quality inputs poses a significant challenge. Recent progress in image restoration has demonstrated the efficacy of learning large models capable of addressing various degradations simultaneously. None
Externí odkaz:
http://arxiv.org/abs/2405.15475