Pose space deformation

Last updated

Pose space deformation is a computer animation technique which is used to deform a mesh on skeleton-driven animation. Common use of this technique is to deform the shape of a mesh (for example, an arm) according to the angle of the joint (in this case, the elbow) bent. Although the name is commonly called Pose space deformation on many scholarly articles, 3D animation software rarely uses that name. On Autodesk Maya, it's implemented under the name Pose Deformer, and on Blender, it's implemented as Corrective Shape Keys. The first famous application of this technique was the cloth's movement on the first episode of the animated film The Animatrix. Industrial Light & Magic used a linear variant of this approach as one of the tools to animate the Hulk for The Avengers movie.

Contents

Fundamentally, pose space deformation (PSD) poses animation as an alternative class of interpolation. Rather than interpolate in time, as with animation curves, or over space, as with meshes, PSD views animation as interpolation over the domain of the character's pose.  PSD was an early use of machine learning and neural networks in computer graphics: the radial basis interpolation that is often used to implement PSD is equivalent to a neural network with a radial nonlinearity. [1]

Working with skeletal-animation

PSD (Pose-Space Deformation) is often used in conjunction with skeletal animation to address some of its key limitations. In skeletal animation, a skeleton is linked to a 3D mesh using a technique called skinning. [2] This connection between the skeleton and the mesh is typically established in a neutral pose, such as a T-pose. Vertices of the mesh are weighted and associated with one or more joints in the skeleton, and as the skeleton moves, the mesh deforms based on an interpolation of the associated joint movements.

However, this approach has limitations. [3] Since it relies on a single neutral pose, it cannot effectively capture dynamic changes in muscle bulging, skin stretching, or the visibility of bones during movement—such as when an elbow bends. Additionally, skeletal animation often struggles with maintaining volume, especially in areas like the elbows and shoulders, where bending joints can cause undesirable deformations.

This is where Pose-Space Deformation comes in. PSD addresses these issues by allowing artists to create multiple poses, each representing a different shape or volume for specific key poses. Instead of relying solely on the skeleton's deformation, PSD adds corrective shapes on top of the skeletal animation to account for changes like muscle bulging, joint protrusion, or the preservation of volume around complex areas like the armpits and elbows. [3] Artists can sculpt these additional poses to ensure that, for example, muscles bulge appropriately when the arm is flexed, or the elbow maintains its proper shape when bent.

Each sculpted pose in PSD is tied to a specific position of the skeleton, allowing for more accurate, nuanced deformations. This combination of skeletal animation and pose-based correction significantly enhances the realism of character movement, especially in areas where volume and surface detail are crucial.

Articles

Related Research Articles

<span class="mw-page-title-main">Rendering (computer graphics)</span> Process of generating an image from a model

Rendering is the process of generating a photorealistic or non-photorealistic image from input data such as 3D models. The word "rendering" originally meant the task performed by an artist when depicting a real or imaginary thing. Today, to "render" commonly means to generate an image or video from a precise description using a computer program.

<span class="mw-page-title-main">Computer animation</span> Art of creating moving images using computers

Computer animation is the process used for digitally generating moving images. The more general term computer-generated imagery (CGI) encompasses both still images and moving images, while computer animation only refers to moving images. Modern computer animation usually uses 3D computer graphics.

Autodesk 3ds Max, formerly 3D Studio and 3D Studio Max, is a professional 3D computer graphics program for making 3D animations, models, games and images. It is developed and produced by Autodesk Media and Entertainment. It has modeling capabilities and a flexible plugin architecture and must be used on the Microsoft Windows platform. It is frequently used by video game developers, many TV commercial studios, and architectural visualization studios. It is also used for movie effects and movie pre-visualization. 3ds Max features shaders, dynamic simulation, particle systems, radiosity, normal map creation and rendering, global illumination, a customizable user interface, and its own scripting language.

<span class="mw-page-title-main">Ragdoll physics</span> Type of procedural animation used by physics engines

Ragdoll physics is a type of procedural animation used by physics engines, which is often used as a replacement for traditional static death animations in video games and animated films. As computers increased in power, it became possible to do limited real-time physical simulations, which made death animations more realistic.

<span class="mw-page-title-main">Skeletal animation</span> Computer animation technique

Skeletal animation or rigging is a technique in computer animation in which a character is represented in two parts: a polygonal or parametric mesh representation of the surface of the object, and a hierarchical set of interconnected parts, a virtual armature used to animate the mesh. While this technique is often used to animate humans and other organic figures, it only serves to make the animation process more intuitive, and the same technique can be used to control the deformation of any object—such as a door, a spoon, a building, or a galaxy. When the animated object is more general than, for example, a humanoid character, the set of "bones" may not be hierarchical or interconnected, but simply represent a higher-level description of the motion of the part of mesh it is influencing.

<span class="mw-page-title-main">Polygon mesh</span> Set of polygons to define the surface of a 3D model

In 3D computer graphics and solid modeling, a polygon mesh is a collection of vertices, edges and faces that defines the shape of a polyhedral object's surface. It simplifies rendering, as in a wire-frame model. The faces usually consist of triangles, quadrilaterals (quads), or other simple convex polygons (n-gons). A polygonal mesh may also be more generally composed of concave polygons, or even polygons with holes.

In the field of 3D computer graphics, a subdivision surface is a curved surface represented by the specification of a coarser polygon mesh and produced by a recursive algorithmic method. The curved surface, the underlying inner mesh, can be calculated from the coarse mesh, known as the control cage or outer mesh, as the functional limit of an iterative process of subdividing each polygonal face into smaller faces that better approximate the final underlying curved surface. Less commonly, a simple algorithm is used to add geometry to a mesh by subdividing the faces into smaller ones without changing the overall shape or volume.

<span class="mw-page-title-main">Non-photorealistic rendering</span> Style of rendering

Non-photorealistic rendering (NPR) is an area of computer graphics that focuses on enabling a wide variety of expressive styles for digital art, in contrast to traditional computer graphics, which focuses on photorealism. NPR is inspired by other artistic modes such as painting, drawing, technical illustration, and animated cartoons. NPR has appeared in movies and video games in the form of cel-shaded animation as well as in scientific visualization, architectural illustration and experimental animation.

<span class="mw-page-title-main">Geometry processing</span>

Geometry processing is an area of research that uses concepts from applied mathematics, computer science and engineering to design efficient algorithms for the acquisition, reconstruction, analysis, manipulation, simulation and transmission of complex 3D models. As the name implies, many of the concepts, data structures, and algorithms are directly analogous to signal processing and image processing. For example, where image smoothing might convolve an intensity signal with a blur kernel formed using the Laplace operator, geometric smoothing might be achieved by convolving a surface geometry with a blur kernel formed using the Laplace-Beltrami operator.

<span class="mw-page-title-main">Human image synthesis</span> Computer generation of human images

Human image synthesis is technology that can be applied to make believable and even photorealistic renditions of human-likenesses, moving or still. It has effectively existed since the early 2000s. Many films using computer generated imagery have featured synthetic images of human-like characters digitally composited onto the real or other simulated film material. Towards the end of the 2010s deep learning artificial intelligence has been applied to synthesize images and video that look like humans, without need for human assistance, once the training phase has been completed, whereas the old school 7D-route required massive amounts of human work .

<span class="mw-page-title-main">Soft-body dynamics</span> Computer graphics simulation of deformable objects

Soft-body dynamics is a field of computer graphics that focuses on visually realistic physical simulations of the motion and properties of deformable objects. The applications are mostly in video games and films. Unlike in simulation of rigid bodies, the shape of soft bodies can change, meaning that the relative distance of two points on the object is not fixed. While the relative distances of points are not fixed, the body is expected to retain its shape to some degree. The scope of soft body dynamics is quite broad, including simulation of soft organic materials such as muscle, fat, hair and vegetation, as well as other deformable materials such as clothing and fabric. Generally, these methods only provide visually plausible emulations rather than accurate scientific/engineering simulations, though there is some crossover with scientific methods, particularly in the case of finite element simulations. Several physics engines currently provide software for soft-body simulation.

Interactive skeleton-driven simulation is a scientific computer simulation technique used to approximate realistic physical deformations of dynamic bodies in real-time. It involves using elastic dynamics and mathematical optimizations to decide the body-shapes during motion and interaction with forces. It has various applications within realistic simulations for medicine, 3D computer animation and virtual reality.

<span class="mw-page-title-main">Andrew Witkin</span> American computer scientist (1952–2010)

Andrew Paul Witkin was an American computer scientist who made major contributions in computer vision and computer graphics.

<span class="mw-page-title-main">Morph target animation</span>

Morph target animation, per-vertex animation, shape interpolation, shape keys, or blend shapes is a method of 3D computer animation used together with techniques such as skeletal animation. In a morph target animation, a "deformed" version of a mesh is stored as a series of vertex positions. In each key frame of an animation, the vertices are then interpolated between these stored positions.

<span class="mw-page-title-main">Nickson Fong</span> Singaporean computer graphics artist

Nickson Fong is a Singaporean computer graphics artist and the first Singaporean to receive an Academy Award.

Physically based animation is an area of interest within computer graphics concerned with the simulation of physically plausible behaviors at interactive rates. Advances in physically based animation are often motivated by the need to include complex, physically inspired behaviors in video games, interactive simulations, and movies. Although off-line simulation methods exist to solve most all of the problems studied in physically-based animation, these methods are intended for applications that necessitate physical accuracy and slow, detailed computations. In contrast to methods common in offline simulation, techniques in physically based animation are concerned with physical plausibility, numerical stability, and visual appeal over physical accuracy. Physically based animation is often limited to loose approximations of physical behaviors because of the strict time constraints imposed by interactive applications. The target frame rate for interactive applications such as games and simulations is often 25-60 hertz, with only a small fraction of the time allotted to an individual frame remaining for physical simulation. Simplified models of physical behaviors are generally preferred if they are more efficient, easier to accelerate, or satisfy desirable mathematical properties. Fine details are not important when the overriding goal of a visualization is aesthetic appeal or the maintenance of player immersion since these details are often difficult for humans to notice or are otherwise impossible to distinguish at human scales.

<span class="mw-page-title-main">Nadia Magnenat Thalmann</span> Computer scientist

Nadia Magnenat Thalmann is a computer graphics scientist and robotician and is the founder and head of MIRALab at the University of Geneva. She has chaired the Institute for Media Innovation at Nanyang Technological University (NTU), Singapore from 2009 to 2021.

<span class="mw-page-title-main">Michael Kass</span> American computer scientist

Michael Kass is an American computer scientist best known for his work in computer graphics and computer vision. He has won an Academy Award and the SIGGRAPH Computer Graphics Achievement Award and is an ACM Fellow.

Nelson Max is a professor of computer science at the University of California at Davis. He received his Ph.D. in Mathematics from Harvard University in 1967, advised by Herman Gluck. His research interests include scientific visualization, computer animation, photorealistic computer graphics rendering, multi-view stereo reconstruction, and augmented reality. In his visualization section, he worked on molecular graphics, and volume and flow visualization, particularly on irregular finite element meshes. He has rendered realistic lighting effects in clouds, trees, and water waves, and has produced numerous computer animations, shown at the annual ACM SIGGRAPH conferences, and in OMNIMAX stereo at the Fujitsu Pavilions at Expo ’85 in Tsukuba Japan, and at Expo ’90 in Osaka Japan. He received the prestigious Steven A. Coons Award in 2007, and is a Fellow of the ACM and a member of the ACM SIGGRAPH Academy.

<span class="mw-page-title-main">Virtual human</span> Computer simulation of a person

A virtual human is a software fictional character or human being. Virtual humans have been created as tools and artificial companions in simulation, video games, film production, human factors and ergonomic and usability studies in various industries, clothing industry, telecommunications (avatars), medicine, etc. These applications require domain-dependent simulation fidelity. A medical application might require an exact simulation of specific internal organs; film industry requires highest aesthetic standards, natural movements, and facial expressions; ergonomic studies require faithful body proportions for a particular population segment and realistic locomotion with constraints, etc.

References

  1. ↑ Bishop, Christopher M. (1995). Neural networks for pattern recognition. Oxford: Clarendon Press. ISBN   0-19-853849-9. OCLC   33101074.
  2. ↑ Kavan, Ladislav (2014-07-27). "Skinning: Real-time shape deformation (Full text not available)" (PDF). ACM SIGGRAPH 2014 Courses. ACM. p. 1. doi:10.1145/2614028.2615427. ISBN   978-1-4503-2962-0.
  3. 1 2 3 Lewis, J.P. (August 2014). "Part III: Example-based Shape Deformation" (PDF). Skinning: Real-time Shape Deformation ACM SIGGRAPH 2014 Course. Retrieved 27 December 2021.
  4. ↑ Lewis, J. P.; Cordner, Matt; Fong, Nickson (1 July 2000). Pose space deformation: A unified approach to shape interpolation and skeleton-driven deformation. ACM Press/Addison-Wesley Publishing Co. pp. 165–172. doi:10.1145/344779.344862. ISBN   978-1-58113-208-3. S2CID   12672235.{{cite book}}: |website= ignored (help)
  5. ↑ Lee, Gene; Hanner, F. (2009), "Practical Experiences with Pose Space Deformation" (PDF), ACM SIGGRAPH
  6. ↑ Cohen Bengio, Julien; Goldenthal, Rony (2013). "Simplicial interpolation for animating the Hulk". ACM SIGGRAPH 2013 Talks. SIGGRAPH '13. Anaheim, California: Association for Computing Machinery. p. 1. doi:10.1145/2504459.2504468. ISBN   9781450323444 . Retrieved October 21, 2024.


This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.