Bicubic interpolation

About: Bicubic interpolation is a research topic. Over the lifetime, 3348 publications have been published within this topic receiving 73126 citations.

Frequency Separation for Real-World Super-Resolution.

Abstract: Most of the recent literature on image super-resolution (SR) assumes the availability of training data in the form of paired low resolution (LR) and high resolution (HR) images or the knowledge of the downgrading operator (usually bicubic downscaling). While the proposed methods perform well on standard benchmarks, they often fail to produce convincing results in real-world settings. This is because real-world images can be subject to corruptions such as sensor noise, which are severely altered by bicubic downscaling. Therefore, the models never see a real-world image during training, which limits their generalization capabilities. Moreover, it is cumbersome to collect paired LR and HR images in the same source domain. To address this problem, we propose DSGAN to introduce natural image characteristics in bicubically downscaled images. It can be trained in an unsupervised fashion on HR images, thereby generating LR images with the same characteristics as the original images. We then use the generated data to train a SR model, which greatly improves its performance on real-world images. Furthermore, we propose to separate the low and high image frequencies and treat them differently during training. Since the low frequencies are preserved by downsampling operations, we only require adversarial training to modify the high frequencies. This idea is applied to our DSGAN model as well as the SR model. We demonstrate the effectiveness of our method in several experiments through quantitative and qualitative analysis. Our solution is the winner of the AIM Challenge on Real World SR at ICCV 2019.

Medical image interpolation based on multi-resolution registration

Abstract: We present a novel registration-based image interpolation approach in this paper. The proposed method is divided into two steps: image registration and intensity interpolation. An image registration method is developed to construct a corresponding transformation, which is represented by the bicubic B -spline vector-valued function, between the given images so that the image features are well matched. To match features from coarse to fine, a multi-resolution strategy is applied with different numbers of B -spline control points adopted at various resolution levels. After registration, the intensity values of in-between images are calculated by linear/cubic interpolation along the matching lines. Experimental results demonstrate that our interpolation approach is effective, robust, and capable of producing continuously deformed in-between images with clear shape features.

Computation of global geometric properties of solid objects

Abstract: A computational scheme for determining global geometric properties of solid object models is presented. The method operates directly on the boundary representation of the model. The scheme is tested on a number of models produced by an experimental modelling system. Primitive objects combined for the tests are all represented in terms of parametric bicubic patches.

New edge directed interpolation

Abstract: This paper presents a novel edge orientation adaptive interpolation scheme for resolution enhancement of still images. In order to achieve ideal orientation adaptation, we propose to estimate the local covariance characteristics at low resolution but cleverly use them to direct the interpolation at high resolution based on the resolution invariant property of edge orientation. The orientation adaptive property guarantees the interpolation always go along the edge orientation but not across it. Our new interpolation scheme can generate images with dramatically higher visual quality than linear interpolation techniques while keeping the computational complexity still modest.