4 papers
Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models
Xuelin Shen, Jiayin Xu, Kangsheng Yin +1
The improved semantic understanding of vision-language pretrained (VLP) models has made it increasingly difficult to protect publicly posted images from being exploited by search e…
Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
Xuelin Shen, Yitong Wang, Silin Zheng +3
In the context of Omni-Directional Image (ODI) Super-Resolution (SR), the unique challenge arises from the non-uniform oversampling characteristics caused by EquiRectangular Projec…
Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision
Kangsheng Yin, Quan Liu, Xuelin Shen +3
The image compression model has long struggled with adaptability and generalization, as the decoded bitstream typically serves only human or machine needs and fails to preserve inf…
Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement
Kang Xiao, Xu Wang, Yulin He +2
Full-reference image quality assessment (FR-IQA) models generally operate by measuring the visual differences between a degraded image and its reference. However, existing FR-IQA m…