Automatically synthesizing 3D content from a causal monocular video has become an important problem. Previous works either use no geometry information, or rely on precise 3D geometry information. Therefore, they cannot obtain reasonable results if the 3D structure in the scene is complex, or noisy 3D geometry information is estimated from monocular videos. In this paper, we present an automatic and robust framework to synthesize stereoscopic videos from casual 2D monocular videos. First, 3D geometry information (e.g., camera parameters, depth map) are extracted from the 2D input video. Then a Bayesian-based View Synthesis (BVS) approach is proposed to render high-quality new virtual views for stereoscopic video to deal with noisy 3D geometry information. Extensive experiments on various videos demonstrate that BVS can synthesize more accurate views than other methods, and our proposed framework also be able to generate high-quality 3D videos.

Image deblurring has been a very challenging problem in recent decades. In this article, we propose a high-quality image deblurring method with a novel image prior based on a new imaging system. The imaging system has a newly designed sensor pattern achieved by adding panchromatic (pan) pixels to the conventional Bayer pattern. Since these pan pixels are sensitive to all wavelengths of visible light, they collect a significantly higher proportion of the light striking the sensor. A new demosaicing algorithm is also proposed to restore full-resolution images from pixels on the sensor. The shutter speed of pan pixels is controllable to users. Therefore, we can produce multiple images with different exposures. When long exposure is needed under dim light, we read pan pixels twice in one shot: one with short exposure and the other with long exposure. The long-exposure image is often blurred, while the short-exposure image can be sharp and noisy. The short-exposure image plays an important role in deblurring, since it is sharp and there is no alignment problem for the one-shot image pair. For the algorithmic aspect, our method runs in a two-step maximum-a-posteriori (MAP) fashion under a joint minimization of the blur kernel and the deblurred image. The algorithm exploits a combined image prior with a statistical part and a spatial part, which is powerful in ringing controls. Extensive experiments under various conditions and settings are conducted to demonstrate the performance of our method.

In this paper an image fusion approach is proposed for denoising digital images corrupted with signal-independent and signal-dependent noise. In the proposed approach, multiple captures of the same scene of interest are acquired and fused to estimate the original, noise-free image. This approach is motivated by the fact that noise is random in nature; hence, its interaction with the pixels will change with each capture, which in turn can be exploited for denoising purposes. In order to fuse multiple captures, a local affine model is developed to relate these captures and the corresponding original image. Furthermore, total variation (TV) regularization, which preserves discontinuity and is robust to noise, is used to solve the local affine fusion model iteratively to estimate the original image. While the proposed approach requires multiple captures, it is still computationally very fast and the quality of the denoised images clearly indicates the feasibility of the proposed approach.

The natural image prior has been proven to be a powerful tool for image deblurring in recent years, though its performance against noise in various applications has not been thoroughly studied. In this paper, we present a multigrid natural image prior for image deconvolution that enhances its robustness against noise, and afford three applications of image deconvolution using this prior: deblurring, super-resolution, and denoising. The prior is based on a remarkable property of natural images that derivatives with different resolutions are subject to the same heavy-tailed distribution with a spatial factor. It can serve in both blind and non-blind deconvolutions. The performances of the proposed prior in different applications are demonstrated by corresponding experimental results.

The visibility of binary image noise at low-to-medium dot densities of current binary printers, i.e 300-400 dots/in, is not subthreshold. Standard halftoning algorithms such as clustered-dot or dispersed-dot dither produce periodic patterns at these dot densities that are easily visible at normal viewing distances in uniform areas. A novel method of halftoning computer-generated uniform areas that reduces noise visibility by using a database of minimum visual modulation bit patterns is introduced. Applications include all paint-by-numbers prints such as those that offer tint-fill or object highlighting.>