Pierre Poulin

Université de Montréal | UdeM · Department of Computer Science and Operations Research

We present a novel up-resing technique for generating high-resolution liquids based on scene flow estimation using deep neural networks. Our approach infers and synthesizes small- and large-scale details solely from a low-resolution particle-based liquid simulation. The proposed network leverages neighborhood contributions to encode inherent liquid...

We present a novel up-resing technique for generating high-resolution liquids based on scene flow estimation using deep neural networks. Our approach infers and synthesizes small- and large-scale details solely from a low-resolution particle-based liquid simulation. The proposed network leverages neighborhood contributions to encode inherent liquid...

Man‐made objects commonly exhibit rounded edges and corners generated through their manufacturing processes. The variation of surface normals at these confined locations produces shading details that are visually essential to the realism of synthetic scenes. The more specular the surface, the finer and more prominent its highlights. However, most g...

Realistic and detailed liquid splashes require costly fine-scale discretization. We present an efficient post-processing approach for particle-based methods to locally improve the behavior of splashes on coarser liquids. Our method first computes a splash volume over time from the intersections between an identified upsampling volume and colliding...

Many manufactured objects and worn surfaces exhibit rounded corners and edges. These fine details are a source of sharp highlights and shading effects, important to our perception between joining surfaces. However, their representation is often neglected because they introduce complex geometric meshing in very small areas. This paper presents a new...

The discretization of fluids can significantly affect computation times of traditional SPH methods. Even if state-of-the-art SPH methods such as divergence-free SPH (DFSPH) produce excellent small-scale details for complex scenarios, simulating a large volume of liquid with these particle-based approaches is still highly expensive considering that...

Lossy texture compression is increasingly used to reduce GPU memory and bandwidth consumption. However, evaluating the quality of compressed textures is a difficult problem. Indeed using PSNR on texture images, like done in most applications, may not be a correct way to proceed. In particular, there is evidence that masking effects apply when the t...

Non-photorealistic rendering (NPR) can use various parameters and techniques to automatically generate a wide range of images with different painterly appearances. However, a real painting is the result of a creative process, and traditionally, many artists have developed their own media, styles, and techniques. Fortunately, the computer can also b...

We present a novel approach for the interactive synthesis and editing of virtual worlds. Our method is inspired by painting operations and uses methods for statistical example-based synthesis to automate content synthesis and deformation. Our real-time approach takes a form of local inverse procedural modeling based on intermediate statistical mode...

We present a geometric representation of a tetrahedral mesh that is solely based on dihedral angles. We first show that the shape of a tetrahedral mesh is completely defined by its dihedral angles. This proof leads to a set of angular constraints that must be satisfied for an immersion to exist in R-3. This formulation lets us easily specify condit...

We introduce a novel fitting procedure that takes as input an arbitrary material, possibly anisotropic, and automatically converts it to a microfacet BRDF. Our algorithm is based on the property that the distribution of microfacets may be retrieved by solving an eigenvector problem that is built solely from backscattering samples. We show that the...

Software evolution history is usually represented at fine granularity by commits in software repositories, and at coarse granularity by software releases. In order to gain insights on development activities and on software evolution, the information on releases is too general, whereas the information on commits is prohibitively large to be efficien...

Combining procedural generation and user control is a fundamental challenge for the interactive design of natural scenery. This is particularly true for modelling complex waterfall scenes where, in addition to taking charge of geometric details, an ideal tool should also provide a user with the freedom to shape the running streams and falls, while...

Understanding a program from its execution traces is extremely difficult because a trace consists of thousands to millions of events, such as method calls, object creation and destruction, etc. Nonetheless, execution traces can provide valuable information, once abstracted from their low-level events. We propose to identify feature-level phases bas...

Directional regularization offers great potential to improve the convergence rates of Monte-Carlo-based global illumination algorithms. In this paper, we show how it can be applied successfully by combining unbiased bidirectional strategies, photon mapping, and biased directional regularization.

In order to interactively render large virtual worlds, the amount of 3D geometry passed to the graphics hardware must be kept to a minimum. Typical solutions to this problem include the use of potentially visible sets and occlusion culling, however, these solutions do not scale well, in time nor in memory, with the size of a virtual world. We propo...

We present Linear Efficient Antialiased Displacement and Reflectance (LEADR) mapping, a reflectance filtering technique for displacement mapped surfaces. Similarly to LEAN mapping, it employs two mipmapped texture maps, which store the first two moments of the displacement gradients. During rendering, the projection of this data over a pixel is use...

Interactive software visualization offers a promising support for program comprehension, including program dynamicity. We present, the extension of an existing visualization tool with heat maps to explore the time and other dimensions of software. To this end, we first propose a framework to unify the two main software dynamicities, execution and e...

We propose a method for mapping polynomial volumes. Given a closed surface and an initial template volume grid, our method deforms the template grid by fitting its boundary to the input surface while minimizing a volume distortion criterion. The result is a point‐to‐point map distorting linear cells into curved ones. Our method is based on several...

Applying non-linear transfer functions and look-up tables to procedural functions (such as noise), surface attributes, or even surface geometry are common strategies used to enhance visual detail. As with any textured or geometric detail, proper filtering is needed to reduce aliasing when viewed across a range of distances, but accurate and efficie...

The representation of material appearance requires an understanding of the underlying structures of real surfaces, light-material interaction, and human visual system. The Bidirectional Texture Function (BTF) describes real-world materials as a spatial variation of reflectance, which depends on view and light directions. Real BTFs integrate all opt...

Color map textures applied directly to surfaces, to geometric microsurface details, or to procedural functions (such as noise), are commonly used to enhance visual detail. Their simplicity and ability to mimic a wide range of realistic appearances have led to their adoption in many rendering problems. As with any textured or geometric detail, prope...

Shadows in 3D games don’t always play nicely with other ways artists make their games look good, especially when you look at how the shadow falls on the model that’s casting it. 3D experts Andrew Woo and Pierre Poulin explain four workarounds for common self-shadowing issues.

Over the last two decades, much effort has been devoted to accurately measure Bidirectional Reflectance Distribution Functions (BRDFs) of real-world materials and to efficiently use the resulting data during the rendering process. Because of their size, it is difficult to directly use measured BRDFs for real-time applications, and fitting the most...

The full article can be found on http://www.cgw.com/Publications/CGW/2012/Volume-35-Issue-6-Oct-Nov-2012-/Viewpoint.aspx#.UZVYl3rn8dU.

In this paper, we tackle the problem of generalizing conformal maps to volumetric meshes. Current methods seek for harmonicity but unfortunately, no computational methods optimize conformality in the volumetric context. As it is proven that conformal maps do not exist for general volume transformations, we seek to optimize shape preservation with a...

Shadow Algorithms Data Miner provides a high-level understanding of the complete set of shadow concepts and algorithms, addressing their usefulness from a larger graphics system perspective. It discusses the applicability and limitations of all the direct illumination approaches for shadow generation. With an emphasis on shadow fundamentals, the b...

This issue features four articles on material appearance, which is important in many computer graphics applications. Two articles on general methods consider two distinct issues: measurement and efficient rendering. The other articles examine two extremely different types of specialized materials, illustrating the variety of application requirement...

We present a general method enhancing the robustness of estimators based on multiple importance sampling (MIS) in a numerical integration context. MIS minimizes variance of estimators for a given sampling configuration, but when this configuration is less adapted to the integrand, the resulting estimator suffers from extra variance. We address this...

This paper presents a simple and general modeling primitive, called a block, based on a generalized cuboid shape. Blocks are laid out and connected together to constitute the base shape of complex objects, from which is extracted a control mesh that can contain both smooth and sharp edges. The volumetric nature of the blocks allows for easy topolog...

This paper presents a reformulation of bidirectional path-tracing that adequately divides the algorithm into pro-cesses efficiently executed in parallel on both the CPU and the GPU. We thus benefit from high-level optimization techniques such as double buffering, batch processing, and asyncronous execution, as well as from the exploitation of most...

We present a system to procedurally generate complex models with interdependent elements. Our system relies on the concept of components to spatially and semantically define various elements. Through a series of successive statements executed on a subset of components selected with queries, we grow a tree of components ultimately defining a model....

The creation of realistic, complex, and diversified virtual worlds is of utmost importance for video games. Unfortunately the amount of time required to create 3D scene contents can be extremely tedious to graphic artists. While procedural modeling can alleviate this task, it has mostly been developed for specific contexts. In this paper, we study...

We present a semi-automated approach for the reverse engineering of UML sequence diagrams. Our approach starts with a set of execution traces that are automatically aligned in order to determine the common behavior. Sequence diagrams are then extracted with an interactive visualization, which allows navigating into execution traces and performing e...

This report presents a volumetric representation that captures low-frequency indirect illumination, structure intended for efficient storage and manipulation of illumination caching and on graphics hardware. It is based on a 3D texture that stores a fixed set of irradiance vectors. This texture is built during a preprocessing step by using almost a...

Raytracing metaballs is a problem that has numerous applications in the rendering of dynamic soft objects such as fluids. However, current techniques are either limited in the visual effects that they can render or their performance drops as the number of metaballs and their density increase. We present a new acceleration structure based on BVH and...

Software visualization is an efficient and flexible tool to inspect and analyze software data at various levels of detail. However, software analysts typically do not have a sufficient background in visualization and cognitive science to select efficient representations and parameters without the help of visualization experts. To overcome this prob...

While existing spherical parameterization algorithms are limited to genus-0 geometrical models, we believe a wide class of models of arbitrary genus can also benefit from the spherical domain. We present a complete and robust pipeline that can generate spherical geometry images from arbitrary genus surfaces where the holes are explicitly represente...

Metaballs [Bloomenthal 1997] are effective to represent fluids and similar complex and deformable geometries, but their implicit nature makes difficult their visualization in real time. A common strategy is to tessellate the resulting isosurface and to render it on GPU, but it scales poorly as the number of metaballs increases. Kanamori et al. [200...

A geometry image offers a simple and compact way of encoding the geometry of a surface and its implicit connectivity in an image-like data structure. It has been shown to be useful in multiple applications because of its suitability for efficient hardware rendering, level of detail, filtering, etc. Most existing algorithms generate geometry images...

Cultural Heritage scenes usually consist of very large and detailed 3D objects with high geometric complexity. Even the raw visualization of such 3D objects already involves a large amount of memory and computation time. When trying to improve the sense of immersion and realism by using, global illumination techniques the demand on these resources...

Assessing software quality and understanding how events in its evolution have lead to anomalies are two important steps toward reducing costs in software maintenance. Unfortunately, evaluation of large quantities of code over several versions is a task too time-consuming, if not overwhelming, to be applicable in general. To address this problem, we...

Streaming data to efficiently render complex 3D scenes in presence of global illumination is still a challenging task. In this paper, we introduce a new data structure based on a 3D grid of irradiance vectors to store the indirect illumination appearing on complex and detailed objects: the Irradiance Vector Grid (IVG). This representation is indepe...

We present an efficient method for importance sampling the product of multiple functions. Our algorithm computes a quick approximation of the product on the fly, based on hierarchical representations of the local maxima and averages of the individual terms. Samples are generated by exploiting the hierarchical properties of many low-discrepancy sequ...

In computer graphics, highlights capture much of the appearance of light reflection off a surface. They are generally limited to pre-defined models (e.g., Phong, Blinn) or to measured data. In this paper, we introduce new tools and a corresponding highlight model to provide computer graphics artists a more expressive approach to design highlights....

Design anomalies, introduced during software evolution, are frequent causes of low maintainability and low flexibility to future changes. Because of the required knowledge, an important subset of design anomalies is difficult to detect automatically, and therefore, the code of anomaly candidates must be inspected manually to validate them. However,...

We present a technique to automatically distill a motion-motif graph from an arbitrary collection of motion capture data. Motion motifs represent clusters of similar motions and together with their encompassing motion graph they lend understandable structure to the contents and connectivity of large motion datasets. They can be used in support of m...

Multiresolution representations of 3D surfaces make it possible to concentrate the efforts of a modification at the appropriate level of detail. This paper introduces a multiresolution representation for point-set surfaces. At each level, the point set is smoothed and downsampled, and the geometric details are encoded along the smoothed surface nor...

There are many applications for which it is necessary to illustrate motion in a static image using visual cues which do not represent a physical entity in the scene, yet are widely understood to convey motion. For example, consider the task of illustrating the desired movements for exercising, dancing, or a given sport technique. Traditional artist...

Motion capture data is an effective way of synthesizing human mo- tion for many interactive applications, including games and simula- tions. A compact, easy-to-decode representation is needed for the motion data in order to support the real-time motion of a large num- ber of characters with minimal memory and minimal computational overheads. We pre...

An important subset of design anomalies is di-cult to de- tect automatically in the code because of the required knowledge. For- tunately, software visualization ofiers an e-cient and ∞exible tool to inspect software data searching for such anomalies. However, as main- tainers typically do not have a background in visualization, they often must see...

A solid partially immersed in a liquid creates a local deformation of the liquid surface at their interface. This deformation, called a meniscus, exhibits high curvature, and as such, produces very intriguing caustic patterns. However, this natural phenomena has been neglected in almost all previous liquid simulation techniques. We propose a comple...

We present a new particle-based method for viscoelastic fluid simulation. We achieve realistic small-scale behavior of substances such as paint or mud as they splash on moving objects. Incompressibility and particle anti-clustering are enforced with a double density relaxation procedure which updates particle positions according to two opposing pre...

We propose an approach for complex software analysis based on visualization. Our work is motivated by the fact that in spite of years of research and practice, software development and maintenance are still time and resource consuming, and high-risk activities. The most important reason in our opin- ion is the complexity of many phenomena related t...

This paper presents a new method of precomputing high-quality soft shadows that can be cast on a static scene as well as on dynamic objects added to that scene. The method efficiently merges the visibility computed from many shadow maps into a penumbra deep shadow map (PDSM) structure. The resulting structure effectively captures the changes of att...

Position. In this position paper, we claim that automatic techniques are limited in the context of quality analysis. We present a semi-automatic approach for quality analysis based on visualization.

We present an interactive reconstruction system based on space carving. The user controls the cam- era and object positions and their impact on the re- construction is immediately displayed. The flow of images is used first for silhouette carving, and then representative images are stored in a hemispheri- cal structure for balanced color carving. P...

Today's hardware graphics accelerators incorporate techniques to antialias edges and minimize geometry-related sampling artifacts. Two such techniques, brute force supersampling and multisampling, increase the sampling rate by rasterizing the triangles in a larger antialiasing buffer that is then filtered down to the size of the framebuffer. The sa...

Modeling complex realistic objects is a difficult and time consuming process. Nevertheless, with improvements in rendering speed and quality, more and more applications require such realistic complex 3D objects. We present an interactive modeling system that extracts 3D objects from photographs. Our key contribution lies in the tight integration of...

Weathering over long periods of time results in cracking and peeling of layers such as paint. To include these ef- fects in computer graphics images it is necessary to sim- ulate crack propagation, loss of adhesion, and the curling effect of paint peeling. We present a new approach which computes such a simulation on surfaces. Our simulation is ins...

Modeling the highly inelastic interactions inside hair, and between the hair and the character body, is a determinant feature for achieving realistic hair animation. However, the extremely large number of hair strands has so far prevented animators from handling these interactions. It is also unclear if they should be treated at the level of indivi...

This paper presents a method for animating long hair while modelling both interactions between the hair and the character's body and between different hair wisps. Our method relies on a layered model paradigm. Hair is structured into a number of volumetric wisps whose motion and deformation are computed using a layered model: A first layer, the ske...

Simplification techniques have mainly been applied on static models. However in movie and game industries, many models are designed to be animated. We extend the progressive mesh technique to handle skeletallyarticulated meshes in order to obtain a continuous levelof -detail (CLOD) representation that retains its ability to be animated. Our techniq...

The goal of this paper is the interactive rendering of 3D trees covering a landscape, with shading and shadows consistent with the lighting conditions. We propose a new IBR representation, consisting of a hierarchy of Bidirectional Textures, which resemble 6D lightfields. A hierarchy of visibility cube-maps is associated to this representation to i...

Caustics produce beautiful and intriguing illumination patterns. However, their complex behavior makes them difficult to simulate accurately in all but the simplest configurations. To capture their appearance, we present an adaptive approach based upon light beams. Exploiting the coherence between the light rays forming a beam greatly reduces the n...

We introduce a set of techniques that are used together to produce realistic-looking animations of burning ob- jects. These include a new method for simulating spread- ing on polygonal meshes. A key component of our ap- proach consists in using individual flames as primitives to animate and render the fire. This simplification en- ables rapid compu...