A5033804298- Advanced Image Processing Techniques
- Image and Video Quality Assessment
- Visual Attention and Saliency Detection
- Advanced Vision and Imaging
- Image Processing Techniques and Applications
- Advanced Optical Imaging Technologies
Lomonosov Moscow State University
2020
A main goal in developing video-compression algorithms is to enhance human-perceived visual quality while maintaining file size. But modern video-analysis efforts such as detection and recognition, which are integral video surveillance autonomous vehicles, involve so much data that they necessitate machine-vision processing with minimal human intervention. In cases, the codec must be optimized for machine vision. This paper explores effects of compression on recognition (objects, faces,...
Shooting video in 3D format can introduce stereoscopic artifacts, potentially causing viewers visual discomfort. In this work, we consider three common artifacts: color mismatch, sharpness and geometric distortion. This paper introduces two neural-network-based methods for simultaneous color- sharpness-mismatch estimation, as well estimating distortions. To train these networks prepared large datasets based on frames from full-length movies compared the results with that previously served...
In this work we present a large-scale analysis of stereoscopic quality for 1,000 VR180 YouTube videos. is new S3D format VR devices which stores the view only single hemisphere. Instead multi-camera rig, requires just two cameras with fisheye lenses similar to conventional 3D-shooting, resulting in cost reduction final device and simplification shooting process. But as format, videos suffer from stereoscopyrelated problems specific 3D shooting. paper analyze detect most common artifacts...