19 papers
From Global to Granular: Revealing IQA Model Performance via Correlation Surface
Baoliang Chen, Danni Huang, Hanwei Zhu +5
Evaluation of Image Quality Assessment (IQA) models has long been dominated by global correlation metrics, such as Pearson Linear Correlation Coefficient (PLCC) and Spearman Rank-O…
LoCAtion: Long-time Collaborative Attention Framework for High Dynamic Range Video Reconstruction
Qianyu Zhang, Bolun Zheng, Lingyu Zhu +3
Prevailing High Dynamic Range (HDR) video reconstruction methods are fundamentally trapped in a fragile alignment-and-fusion paradigm. While explicit spatial alignment can successf…
EduVQA: Towards Concept-Aware Assessment of Educational AI-Generated Videos
Baoliang Chen, Xinlong Bu, Hanwei Zhu +2
Existing AI-generated video quality assessment (AIGVQA) methods mainly focus on global perceptual realism and coarse text-video alignment, while overlooking a critical requirement…
Dual-Latent Collaborative Decoding for Fidelity-Perception Balanced Image Compression
Qi Mao, Zijian Wang, Zhengxue Cheng +2
Learned image compression (LIC) increasingly requires reconstructions that balance distortion fidelity and perceptual realism across a wide range of bitrates. However, most existin…
CADC: Content Adaptive Diffusion-Based Generative Image Compression
Xihua Sheng, Lingyu Zhu, Tianyu Zhang +3
Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential…
Low-light Image Enhancement with Retinex Decomposition in Latent Space
Bolun Zheng, Qingshan Lei, Quan Chen +4
Retinex theory provides a principled foundation for low-light image enhancement, inspiring numerous learning-based methods that integrate its principles. However, existing methods…