prolate
发表于 2025-3-28 18:13:33
http://reply.papertrans.cn/24/2342/234122/234122_41.png
眉毛
发表于 2025-3-28 19:58:50
Learning Image-to-Image Translation Using Paired and Unpaired Training Samplessufficient training data. Traditionally different approaches have been proposed depending on whether aligned image pairs or two sets of (unaligned) examples from both domains are available for training. While paired training samples might be difficult to obtain, the unpaired setup leads to a highly
600
发表于 2025-3-28 23:44:14
http://reply.papertrans.cn/24/2342/234122/234122_43.png
单片眼镜
发表于 2025-3-29 04:30:56
Cross-Spectral Image Patch Matching by Learning Features of the Spatially Connected Patches in a Shams. We consider cross-spectral image patches can be matched because there exists a shared semantic feature space among them, in which the semantic features from different spectral images will be more independent of the spectral domains. To learn this shared feature space, we propose a progressive co
杀死
发表于 2025-3-29 09:46:02
Semantic Segmentation Refinement by Monte Carlo Region Growing of High Confidence Detectionsonnected conditional random fields (CRFs) can significantly refine segmentation predictions. However, they rely on supervised parameter optimization that depends upon specific datasets and predictor modules. We propose an unsupervised method for semantic segmentation refinement that takes as input t
Osteons
发表于 2025-3-29 12:38:10
A Deep Blind Image Quality Assessment with Visual Importance Based Patch Scorelution is splitting the training image into patches, assigning each patch the quality score, while the assignment of patch score is not consistent with the human visual system (HVS) well. To address the problem, we propose a patch quality assignment strategy, introducing the weighting map to describ
弄脏
发表于 2025-3-29 15:47:20
http://reply.papertrans.cn/24/2342/234122/234122_47.png
senile-dementia
发表于 2025-3-29 19:48:04
http://reply.papertrans.cn/24/2342/234122/234122_48.png
Hippocampus
发表于 2025-3-29 23:55:16
SAFE: Scale Aware Feature Encoder for Scene Text Recognitionoder (SAFE) that is designed specifically for encoding characters with different scales. SAFE is composed of a multi-scale convolutional encoder and a scale attention network. The multi-scale convolutional encoder targets at extracting character features under multiple scales, and the scale attentio
Aphorism
发表于 2025-3-30 07:17:01
Neural Abstract Style Transfer for Chinese Traditional Paintingtically appealing. Compared with western artistic painting, it is usually more visually abstract and textureless. Recently, neural network based style transfer methods have shown promising and appealing results which are mainly focused on western painting. It remains a challenging problem to preserv