Parametric texture synthesis for filling holes in pictures
نویسنده
چکیده
This paper presents a framework for “Filling In” missing gaps in images and particularly patches with texture. The underlying idea is to construct a parametric model of the p.d.f. of the texture to be re-synthesised and then draw samples from that p.d.f. to create the resulting reconstruction. A Bayesian approach is used to repose 2D Autoregressive Models as generative models for texture (using the Gibbs sampler) given surrounding boundary conditions. A fast implementation is presented that iterates between pixelwise updates and blockwise parametric model estimation. The novel ideas in this paper are joint parameter estimation and fast, efficient texture reconstruction using linear models.
منابع مشابه
Detail-Preserving Surface Inpainting
Inpainting is a well-known technique in the context of image and art restoration, where paint losses are filled up to the level of the surrounding paint and then coloured to match. Analogue tasks can be found in 3D geometry processing, as digital representations of real-world objects often contain holes, due to hindrances during data acquisition or as a consequence of interactive modelling oper...
متن کاملFragment-based Surface Inpainting
Inpainting is a well-known technique in the context of image and art restoration, where paint losses are filled up to the level of the surrounding paint and then coloured to match. Analogue tasks can be found in 3D geometry processing, as digital representations of real-world objects often contain holes, due to hindrances during data acquisition or as a consequence of interactive modelling oper...
متن کاملNon-parametric synthesis of laminar volumetric textures from a 2D sample
The goal of this paper is to evaluate non-parametric algorithms that achieve 3D texture synthesis from a single 2D sample. The algorithms under study are variants of the algorithm proposed by Wei and Levoy [1]. Several authors have proposed different algorithms that intend to better reproduce, in the output texture, the diversity learned in the input sample. Hence, we turn our attention to the ...
متن کاملAnalysis of Texture Synthesis Algorithms with Respect to Usage for Hole-Filling in 3D Geometry
The development of range scanning technology has offered new possibilities to capture large datasets in computer graphics. Due to physical restrictions, captured 3D objects can contain holes that need to be filled automatically. In a different area of interest, the field of texture synthesis, research has been done on a solution for a similar 2D problem. To utilize available methods, the challe...
متن کاملVideo Completion Using Global Optimization
Video completion is a computer vision technique to restore the holes in video sequences due to removal of the dynamic or static foreground object by filling the unknown region with the known information. In this paper, a novel algorithm for video completion of large holes in video sequences is proposed. Video completion is treated as a global optimization problem by enforcing the spatial-tempor...
متن کامل