Abstract In this short paper, we analyze the problem of finding the triangular barycentric coordinates of an interpolated ray hitting a given point. This task, which we term theinverse barycentric displacement problem, is general and useful in geometry processing and computer graphics. Concrete applications of the solution include the construction of displacement maps and texture baking. We derive the set of complete, closed-form solutions and discuss the number and existence of solutions. We close with a discussion of implementation-oriented optimizations and a few example applications.

Abstract We devise a technique designed to remove the texturing artefacts that are typical of 3D models representing real‐world objects, acquired by photogrammetric techniques. Our technique leverages the recent advancements in inpainting of natural colour images, adapting them to the specific context. A neural network, modified and trained for our purposes, replaces the texture areas containing the defects, substituting them with new plausible patches of texels, reconstructed from the surrounding surface texture. We train and apply the network model on locally reparametrized texture patches, so to provide an input that simplifies the learning process, because it avoids any texture seams, unused texture areas, background, depth jumps and so on. We automatically extract appropriate training data from real‐world datasets. We show two applications of the resulting method: one, as a fully automatic tool, addressing all problems that can be detected by analysing the UV‐map of the input model; and another, as an interactive semi‐automatic tool, presented to the user as a 3D ‘fixing’ brush that has the effect of removing artefacts from any zone the users paints on. We demonstrate our method on a variety of real‐world inputs and provide a reference usable implementation.

Micro-meshes (μ-meshes) are a new structured graphics primitive supporting a large increase in geometric fidelity, without commensurate memory and run-time processing costs, consisting of a base mesh enriched by a displacement map. A new generation of GPUs supports this structure with native hardware μ-mesh ray-tracing, that leverages a self-bounding, compressed displacement mapping scheme to achieve these efficiencies. In this paper, we present anautomatic method to convert an existing multi-million triangle mesh into this compact format, unlocking the advantages of the data representation for a large number of scenarios. We identify the requirements for high-quality μ-meshes, and show how existing re-meshing and displacement-map baking tools are ill-suited for their generation. Our method is based on a simplification scheme tailored to the generation of high-quality base meshes , optimized for tessellation and displacement sampling, in conjunction with algorithms for determining displacement vectors to control the direction and range of displacements. We also explore the optimization of μ-meshes for texture maps and the representation of boundaries. We demonstrate our method with extensive batch processing, converting an existing collection of high-resolution scanned models to the micro-mesh representation, providing an open-source reference implementation, and, as additional material, the data and an inspection tool.

Abstract We propose a method to improve an existing parametrization (UV‐map layout) of a textured 3D model, targeted explicitly at alleviating typical defects afflicting models generated with automatic photo‐reconstruction tools from real‐world objects. This class of 3D data is becoming increasingly important thanks to the growing popularity of reliable, ready‐to‐use photogrammetry software packages. The resulting textured models are richly detailed, but their underlying parametrization typically falls short of many practical requirements, particularly exhibiting excessive fragmentation and consequent problems. Producing a completely new UV‐map, with standard parametrization techniques, and then resampling a new texture image, is often neither practical nor desirable for at least two reasons: first, these models have characteristics (such as inconsistencies, high resolution) that make them unfit for automatic or manual parametrization; second, the required resampling leads to unnecessary signal degradation because this process is unaware of the original texel densities. In contrast, our method improves the existing UV‐map instead of replacing it, balancing the reduction of the map fragmentation with signal degradation due to resampling, while also avoiding oversampling of the original signal. The proposed approach is fully automatic and extensively tested on a large benchmark of photo‐reconstructed models; quantitative evaluation evidences a drastic and consistent improvement of the mappings.