Pierre-Edouard Landes

Processing graphical data, either for its editing or the synthesis of new content, demands a good balance between the different sources of information one may exploit. Unlike "procedural" techniques, synthesis by example stands out thanks to its extreme ease-of-use : indeed, tasks such as identification, analysis and reproduction of the distinguishing features of the user-provided examples are left to the method itself. Such approaches, along with today's intricate editing methods have greatly favored the production of compelling graphical content at a wide scale, and henceforth facilitated the adoption of computer-assisted tools by artists.But in order to meet with success, they also have to be highly controllable without being a mere extension of the artist's hand.

We explore here such concerns in the context of expressive rendering and study the interactions, may they be collaborative or competitive, between the different sources of information at the core of such processes. In our opinion, there are three main sources of information: the automatic analysis of the inputs before processing; the use of prior knowledge through predetermined models; and users' explicit intervention. Through a clever combination of these sources, we propose new expressive synthesis techniques which satisfy the aforementioned usability. More than photographic realism, expressive rendering strives for the fulfillment of less easily quantifiable goals such as the intelligibility or the aesthetic value of its results. The subjectivity behind the assessment of such criteria thus forces us to attach much importance to the careful choice of the source of information to favor; the required amount of user intervention (without being detrimental to the method's theoretical value); and the possible resort to prior models (without endangering its generality).

Three main synthesis instances are studied in this document: texture generation, image de-colorization, and artistic line rendering. The great disparity of inputs (raster and vector textures, complex images, 3d meshes), terms of synthesis (imitation, conversion, depiction) and objectives (preservation of a texture's visual signature, plausible restitution of chromatic contrasts, creation of drawings in accordance with users' styles) gives rise to distinct balances between those sources of information and requires the consideration of various modes of user interaction.

We present a novel shape-aware method for synthesizing 2D and 3D discrete element textures consisting of collections of distinct vector graphics objects. Extending the long-proven point process framework, we propose a shape process, a novel stochastic model based on spatial measurements that fully take into account the geometry of the elements. We demonstrate that our approach is well-suited for discrete texture synthesis by example. Our modelenables for both robust statistical parameter estimation and reliable output generation by Monte Carlo sampling. Our numerous experiments show that contrary to current state-of-the-art techniques, our algorithm manages to capture anisotropic element distributions and systematically prevents undesirable collisions between objects.

We present a technique for the analysis and re-synthesis of 2D arrangements of stroke-based vector elements. The capture of an artist's style by the sole posterior analysis of his/her achieved drawing poses a formidable challenge. Such by-example techniques could become one of the most intuitive tools for users to alleviate creation process efforts. Here, we propose to tackle this issue from a statistical point of view and take specific care of accounting for information usually overlooked in previous research, namely the elements' very appearance. Composed of curve-like strokes, we describe elements by a concise set of perceptually relevant features. After detecting appearance dominant traits, we can generate new arrangements that respect the captured appearance-related spatial statistics using multitype point processes. Our method faithfully reproduces visually similar arrangements and relies on neither heuristics nor post-processes to ensure statistical correctness.

The basic problem of greyscale transformation is to reproduce the intent of the colour original, its contrasts and salient features, while preserving the perceived magnitude and direction of its gradients. The transformation consists of two interdependent tasks: a mapping that assigns a grey value to each pixel or colour, and a discriminability constraint so that the achromatic differences match their corresponding original colour differences. Recent approaches solve discriminability constraints to determine the grey values, producing images in which the original colour contrasts are highly discriminable. However, the greyscale images may exhibit exaggerated dynamic range, an arbitrary achromatic order that differs among colour palettes, and a smoothing or masking of details. These modifications all contribute to make the grey version appear dissimilar from its original and create inconsistency among like images and video frames.

The goal of this work is to create a perceptually accurate version of the colour image that represents its psychophysical effect on a viewer. Such greyscale imagery is important for printed textbooks and catalogues, the stylization of videos and for display on monochromatic medical displays. A perceptually accurate image is one that emulates both global and local impressions: it matches the original values' range and average luminance, its local contrasts are neither exaggerated nor understated, its grey values are ordered according to colour appearance and differences in spatial details are imperceptible. Strong perceptual similarity is particularly important for consistency over varying palettes and temporal coherence for animations.

The basic problem of greyscale transformation is to reproduce the intent of the colour original, its contrasts and salient features, while preserving the perceived magnitude and direction of its gradients. The transformation consists of two interdependent tasks: a mapping that assigns a grey value to each pixel or colour, and a discriminability constraint so that the achromatic differences match their corresponding original colour differences. Recent approaches solve discriminability constraints to determine the grey values, producing images in which the original colour contrasts are highly discriminable. However, the greyscale images may exhibit exaggerated dynamic range, an arbitrary achromatic order that differs among colour palettes, and a smoothing or masking of details. These modifications all contribute to make the grey version appear dissimilar from its original and create inconsistency among like images and video frames.

The goal of this work is to create a perceptually accurate version of the colour image that represents its psychophysical effect on a viewer. Such greyscale imagery is important for printed textbooks and catalogues, the stylization of videos and for display on monochromatic medical displays. A perceptually accurate image is one that emulates both global and local impressions: it matches the original values' range and average luminance, its local contrasts are neither exaggerated nor understated, its grey values are ordered according to colour appearance and differences in spatial details are imperceptible. Strong perceptual similarity is particularly important for consistency over varying palettes and temporal coherence for animations.

In this work we propose a jitter/correction approach producing a discrete combination of the inputs strokes, as inspired by [Risser et al. 2010; Kalogerakis et al. 2012]. Starting from one of the input doodles, we exchange each stroke by jittering it in a convenient feature space that gathers all the strokes from all input doodles. A geometric relaxation step ensures that the local spatial organization of the strokes is still plausible with regard to the given examplars.

Existing example-based texture synthesis techniques are inherently unadapted to textures consisting of a set of randomly disposed, individually discernible shapes. Local methods striving at pixel-based discontinuity reduction hardly preserve input's long-range structures. Alternatively, research built upon the supposed respect by the input's features of given placement rules are too restrictive to be straightly extended to stochastic arrangements.

In this paper we present a new method for analyzing and resynthesizing such arrangements. Our objective is to acquire their constitutive shapes to enable structure-aware resynthesis. What characterizes such shapes is their repetition throughout the input. We exploit this trait by recording recurrences of visually similar neighborhoods which are later extended to regions. We bring those together to compute the input's coverage map and extract final repetitive shapes. By directly manipulating shapes, resynthesis can be enriched with high-level information unavailable in pixel-based approaches. We gather statistics on their placement and appearance variations and use those to produce new images. To achieve this, we draw inspiration and improve techniques for capturing element arrangements, techniques once limited to vectorized NPR primitives.