Non-parametric Texture Transfer Using MeshMatch
نویسندگان
چکیده
Transferring surface properties such as color texture from one 3D mesh to another is a well-known problem, which has become increasingly important as the demand for textured models in games and films has grown. We propose a mesh-based analogy of the PatchMatch [Barnes et al. 2009] algorithm, which we call “MeshMatch,” and a non-parametric multi-resolution approach to surface texture transfer based on this algorithm. Our system offers benefits of both parameterization and texture synthesis approaches, preserving both largeand fine-scale patterns of the source properties. We demonstrate this system in a variety of applications, including texture transfer, detail transfer, and texture painting assists.
منابع مشابه
Direct Geometric Texture Synthesis and Transfer on 3D Meshes
We present a technique for the transfer and synthesis of geometric texture on 3D surface meshes. Our technique combines localised surface fitting together with non-parametric sampling to facilitate the extraction, transfer and successful synthesis of geometric relief from one surface mesh to another.
متن کاملTexture Recognition Using a Non-Parametric Multi-Scale Statistical Model
We describe a technique for using the joint occurrence of local features at multiple resolutions to measure the similarity between texture images. Though superficially similar to a number of “Gabor” style techniques, which recognize textures through the extraction of multi-scale feature vectors, our approach is derived fvom an accurate generative model of texture, which is explicitly multiscale...
متن کاملTexture Classification using Non-Parametric Markov Random Fields
This thesis investigates texture classification using Non-Parametric Markov Random fields. Texture models using local image descriptors are investigated. Classification performance using such models is then reported upon and the results are used to guide development of future classifiers which take account of scale information within an image. The issues and effects of scale within texture mode...
متن کاملWavelet Based Texture Synthesis
This paper presents a new algorithm for synthesising image texture. Texture synthesis is an important process in image post-production. The best previous approaches have used non-parametric methods for synthesising texture. Unfortunately, these methods generally suffer from high computational cost and difficulty in handling scale in the synthesis process. This paper introduces a new idea of usi...
متن کاملTexture Unmapping – Combining Parametric and Non- Parametric Techniques for Image Reconstruction
We present a new technique, which we call ‘texture unmapping’, and its application to image reconstruction. A parametric model of an image is made, and then subtracted from the image to leave a non-parametric component. The two components may then be reconstructed independently and then recombined to give a final reconstruction. Results of the new technique are given on a range of images.
متن کامل