Sub-pixel resolution

Abstract: This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. A new DIVerse 2K resolution image dataset (DIV2K) was employed. The challenge had 6 competitions divided into 2 tracks with 3 magnification factors each. Track 1 employed the standard bicubic downscaling setup, while Track 2 had unknown downscaling operators (blur kernel and decimation) but learnable through low and high res train images. Each competition had ∽100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

Abstract: Nearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate low resolution input images when appropriately warped and down-sampled to model the image formation process. (These reconstruction constraints are normally combined with some form of smoothness prior to regularize their solution.) We derive a sequence of analytical results which show that the reconstruction constraints provide less and less useful information as the magnification factor increases. We also validate these results empirically and show that, for large enough magnification factors, any smoothness prior leads to overly smooth results with very little high-frequency content. Next, we propose a super-resolution algorithm that uses a different kind of constraint in addition to the reconstruction constraints. The algorithm attempts to recognize local features in the low-resolution images and then enhances their resolution in an appropriate manner. We call such a super-resolution algorithm a hallucination or reconstruction algorithm. We tried our hallucination algorithm on two different data sets, frontal images of faces and printed Roman text. We obtained significantly better results than existing reconstruction-based algorithms, both qualitatively and in terms of RMS pixel error.

Abstract: We present a new post-processing step to enhance the resolution of range images. Using one or two registered and potentially high-resolution color images as reference, we iteratively refine the input low-resolution range image, in terms of both its spatial resolution and depth precision. Evaluation using the Middlebury benchmark shows across-the-board improvement for sub-pixel accuracy. We also demonstrated its effectiveness for spatial resolution enhancement up to 100 times with a single reference image.

Abstract: The spatial resolution of a multispectral digital image is enhanced in a process of the type wherein a higher spatial resolution panchromatic image is merged with a plurality of lower spatial resolution spectral band images. A lower spatial resolution panchromatic image is simulated and a Gram-Schmidt transformation is performed on the simulated lower spatial resolution panchromatic image and the plurality of lower spatial resolution spectral band images. The simulated lower spatial resolution panchromatic image is employed as the first band in the Gram-Schmidt transformation. The statistics of the higher spatial resolution panchromatic image are adjusted to match the statistics of the first transform band resulting from the Gram-Schmidt transformation and the higher spatial resolution panchromatic image (with adjusted statistics) is substituted for the first transform band resulting from the Gram-Schmidt transformation to produce a new set of transform bands. Finally, the inverse Gram-Schmidt transformation is performed on the new set of transform bands to produce the enhanced spatial resolution multispectral digital image.