A Nuclear-norm Model for Multi-Frame Super-Resolution Reconstruction from Video Clips
This work addresses video super-resolution for applications like surveillance or media, but it is incremental as it builds on existing variational and low-rank methods.
The authors tackled the problem of generating super-resolution images from multiple low-resolution video frames by proposing a variational approach with a low-rank model using nuclear-norm regularization, resulting in more accurate images with fewer artifacts and finer details compared to other models.
We propose a variational approach to obtain super-resolution images from multiple low-resolution frames extracted from video clips. First the displacement between the low-resolution frames and the reference frame are computed by an optical flow algorithm. Then a low-rank model is used to construct the reference frame in high-resolution by incorporating the information of the low-resolution frames. The model has two terms: a 2-norm data fidelity term and a nuclear-norm regularization term. Alternating direction method of multipliers is used to solve the model. Comparison of our methods with other models on synthetic and real video clips show that our resulting images are more accurate with less artifacts. It also provides much finer and discernable details.