Abstract
Although multi-frame super resolution has been extensively studied in past decades, super resolving real-world video sequences still remains challenging. In existing systems, either the motion models are oversimplified, or important factors such as blur kernel and noise level are assumed to be known. Such models cannot deal with the scene and imaging conditions that vary from one sequence to another. In this paper, we propose a Bayesian approach to adaptive video super resolution via simultaneously estimating underlying motion, blur kernel and noise level while reconstructing the original high-res frames. As a result, our system not only produces very promising super resolution results that outperform the state of the art, but also adapts to a variety of noise levels and blur kernels. Theoretical analysis of the relationship between blur kernel, noise level and frequency-wise reconstruction rate is also provided, consistent with our experimental results.
Keywords
Motion blurArtificial intelligenceComputer scienceKernel (algebra)Computer visionNoise (video)Bayesian probabilityFrame (networking)Image (mathematics)MathematicsTelecommunications
Affiliated Institutions
Related Publications
Fast and Robust Multiframe Super Resolution
Super-resolution reconstruction produces one or a set of high-resolution images from a set of low-resolution images. In the last two decades, a variety of super-resolution metho...
Space-time super-resolution from a single video
Spatial Super Resolution (SR) aims to recover fine image details, smaller than a pixel size. Temporal SR aims to recover rapid dynamic events that occur faster than the video fr...
Super-Resolution Without Explicit Subpixel Motion Estimation
The need for precise (subpixel accuracy) motion estimates in conventional super-resolution has limited its applicability to only video sequences with relatively simple motions s...
Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR meth...
Image Super-Resolution Via Iterative Refinement
We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models (Ho et al. 2020), (Sohl-Dickstein et al. 2015)...
Publication Info
- Year
- 2011
- Type
- article
- Pages
- 209-216
- Citations
- 250
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
250
OpenAlex
Cite This
Ce Liu,
Deqing Sun
(2011).
A Bayesian approach to adaptive video super resolution.
, 209-216.
https://doi.org/10.1109/cvpr.2011.5995614
Identifiers
- DOI
- 10.1109/cvpr.2011.5995614