A Content-aware Metric for Stitched Panoramic Image Quality Assessment [ ICCV 2017 ]
关于图像质量评价，很早之前就有前辈在该领域做出卓越的贡献，推动该方向的进步。 图像质量评价的重要性自然不言而喻，而且对于世界上很多事物，人们都想着站在某个或多个角度进行一系列评价，或主观或客观。 最开始是针对于单幅照片的一系列评价，从主观评价和客观评价两个大的角度来较为精确评估一幅照片的质量好坏。其中 主观评价分为：绝对评价和相对评价 客观评价分为：全参考评价、部分参考评价和无参考评价 主观评价又
相关文章
- 1. A Survey for Image Quality Assessment（综述）
- 2. Face-Image-Quality-Assessment
- 3. Tone-Mapped Image Quality Assessment
- 4. Image Quality Assessment,IQA and Video Quality Assessment,VQA
- 5. Two-Stream Convolutional Networks for Blind Image Quality Assessment
- 6. A Quality Model for the Systematic Assessment of Requirements Traceability
- 7. Blind image quality assessment via learnable attention-based pooling
- 8. No-reference stereoscopic image quality assessment using a multi-task CNN and registered distortion
- 9. Naturalness-Aware Deep No-Reference Image Quality Assessment
- 10. Stereoscopic image quality assessment combining statistical features and binocular theory
- 更多相关文章...
- • Scala for循环 - Scala教程
- • Lua for 循环 - Lua 教程
- • Docker 清理命令
- • NewSQL-TiDB相关
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. A Survey for Image Quality Assessment（综述）
- 2. Face-Image-Quality-Assessment
- 3. Tone-Mapped Image Quality Assessment
- 4. Image Quality Assessment,IQA and Video Quality Assessment,VQA
- 5. Two-Stream Convolutional Networks for Blind Image Quality Assessment
- 6. A Quality Model for the Systematic Assessment of Requirements Traceability
- 7. Blind image quality assessment via learnable attention-based pooling
- 8. No-reference stereoscopic image quality assessment using a multi-task CNN and registered distortion
- 9. Naturalness-Aware Deep No-Reference Image Quality Assessment
- 10. Stereoscopic image quality assessment combining statistical features and binocular theory