cgi là gì

Morphogenetic Creations computer-generated digital art exhibition by Andy Lomas at Watermans Arts Centre, west London, in 2016

Computer-generated imagery (CGI) is a specific-technology or application of computer graphics for creating or improving images in art, printed truyền thông media, simulators, videos and đoạn phim games. These images are either static (i.e. still images) or dynamic (i.e. moving images). CGI both refers to tướng 2 chiều computer graphics and (more frequently) 3 chiều computer graphics with the purpose of designing characters, virtual worlds, or scenes and special effects (in films, television programs, commercials, etc.). The application of CGI for creating/improving animations is called computer animation, or CGI animation.

Bạn đang xem: cgi là gì


The first feature film to tướng use CGI as well as the composition of live-action film with CGI was Vertigo (1958),[1] which used CGI in the opening credits of the film. The first feature film to tướng make use of CGI with live action in the storyline of the film was the 1973 film Westworld.[2] Other early films that incorporated CGI include Star Wars: Episode IV (1977),[2] Tron (1982),[2] Golgo 13: The Professional (1983),[3] The Last Starfighter (1984),[4] Young Sherlock Holmes (1985) and Toy Story (1995). The first music đoạn phim to tướng use CGI was Dire Straits's award-winning "Money for Nothing" (1985), whose success was instrumental in giving the process mainstream exposure.[citation needed]

The evolution of CGI led to tướng the emergence of virtual cinematography in the 1990s, where the vision of the simulated camera is not constrained by the laws of physics. Availability of CGI software and increased computer speeds have allowed individual artists and small companies to tướng produce professional-grade films, games, and fine art from their trang chính computers.

Static images and landscapes[edit]

A fractal landscape created in Terragen

Not only bởi animated images size part of computer-generated imagery; natural looking landscapes (such as fractal landscapes) are also generated via computer algorithms. A simple way to tướng generate fractal surfaces is to tướng use an extension of the triangular mesh method, relying on the construction of some special case of a de Rham curve, e.g. midpoint displacement.[5] For instance, the algorithm may start with a large triangle, then recursively zoom in by dividing it into four smaller Sierpinski triangles, then interpolate the height of each point from its nearest neighbors.[5] The creation of a Brownian surface may be achieved not only by adding noise as new nodes are created but by adding additional noise at multiple levels of the mesh.[5] Thus a topographical map with varying levels of height can be created using relatively straightforward fractal algorithms. Some typical, easy-to-program fractals used in CGI are the plasma fractal and the more dramatic fault fractal.[6]

Many specific techniques have been researched and developed to tướng produce highly focused computer-generated effects — e.g., the use of specific models to tướng represent the chemical weathering of stones to tướng model erosion and produce an "aged appearance" for a given stone-based surface.[7]

Architectural scenes[edit]

A computer-generated image featuring a house at sunset, made in Blender

Modern architects use services from computer graphic firms to tướng create 3-dimensional models for both customers and builders. These computer generated models can be more accurate phàn nàn traditional drawings. Architectural animation (which provides animated movies of buildings, rather phàn nàn interactive images) can also be used to tướng see the possible relationship a building will have in relation to tướng the environment and its surrounding buildings. The processing of architectural spaces without the use of paper and pencil tools is now a widely accepted practice with a number of computer-assisted architectural design systems.[8]

Architectural modeling tools allow an architect to tướng visualize a space and perform "walk-throughs" in an interactive manner, thus providing "interactive environments" both at the urban and building levels.[9] Specific applications in architecture not only include the specification of building structures (such as walls and windows) and walk-throughs but the effects of light and how sunlight will affect a specific design at different times of the day.[10][11]

Architectural modeling tools have now become increasingly internet-based. However, the quality of internet-based systems still lags behind sophisticated in-house modeling systems.[12]

In some applications, computer-generated images are used to tướng "reverse engineer" historical buildings. For instance, a computer-generated reconstruction of the monastery at Georgenthal in Germany was derived from the ruins of the monastery, yet provides the viewer with a "look and feel" of what the building would have looked lượt thích in its day.[13]

Anatomical models[edit]

A CT pulmonary angiogram image generated by a computer from a collection of x-rays

Computer generated models used in skeletal animation are not always anatomically correct. However, organizations such as the Scientific Computing and Imaging Institute have developed anatomically correct computer-based models. Computer generated anatomical models can be used both for instructional and operational purposes. To date, a large toàn thân of artist produced medical images continue to tướng be used by medical students, such as images by Frank H. Netter, e.g. Cardiac images. However, a number of online anatomical models are becoming available.

A single patient X-ray is not a computer generated image, even if digitized. However, in applications which involve CT scans a three-dimensional model is automatically produced from many single-slice x-rays, producing "computer generated image". Applications involving magnetic resonance imaging also bring together a number of "snapshots" (in this case via magnetic pulses) to tướng produce a composite, internal image.

In modern medical applications, patient-specific models are constructed in 'computer assisted surgery'. For instance, in total knee replacement, the construction of a detailed patient-specific model can be used to tướng carefully plan the surgery.[14] These three-dimensional models are usually extracted from multiple CT scans of the appropriate parts of the patient's own anatomy. Such models can also be used for planning aortic valve implantations, one of the common procedures for treating heart disease. Given that the shape, diameter, and position of the coronary openings can vary greatly from patient to tướng patient, the extraction (from CT scans) of a model that closely resembles a patient's valve anatomy can be highly beneficial in planning the procedure.[15]

Cloth and skin images[edit]

Computer-generated wet fur created in Autodesk Maya

Models of cloth generally fall into three groups:

  • The geometric-mechanical structure at yarn crossing
  • The mechanics of continuous elastic sheets
  • The geometric macroscopic features of cloth.[16]

To date, making the clothing of a digital character automatically fold in a natural way remains a challenge for many animators.[17]

In addition to tướng their use in film, advertising and other modes of public display, computer generated images of clothing are now routinely used by top fashion design firms.[18]

The challenge in rendering human skin images involves three levels of realism:

  • Photo realism in resembling real skin at the static level
  • Physical realism in resembling its movements
  • Function realism in resembling its response to tướng actions.[19]

Xem thêm: công chứng sơ yếu lý lịch

The finest visible features such as fine wrinkles and skin pores are the size of about 100 µm or 0.1 millimetres. Skin can be modeled as a 7-dimensional bidirectional texture function (BTF) or a collection of bidirectional scattering distribution function (BSDF) over the target's surfaces.

Interactive simulation and visualization[edit]

Interactive visualization is the rendering of data that may vary dynamically and allowing a user to tướng view the data from multiple perspectives. The applications areas may vary significantly, ranging from the visualization of the flow patterns in fluid dynamics to tướng specific computer aided design applications.[20] The data rendered may correspond to tướng specific visual scenes that change as the user interacts with the system — e.g. simulators, such as flight simulators, make extensive use of CGI techniques for representing the world.[21]

At the abstract level, an interactive visualization process involves a "data pipeline" in which the raw data is managed and filtered to tướng a size that makes it suitable for rendering. This is often called the "visualization data". The visualization data is then mapped to tướng a "visualization representation" that can be fed to tướng a rendering system. This is usually called a "renderable representation". This representation is then rendered as a displayable image.[21] As the user interacts with the system (e.g. by using joystick controls to tướng change their position within the virtual world) the raw data is fed through the pipeline to tướng create a new rendered image, often making real-time computational efficiency a key consideration in such applications.[21][22]

Computer animation[edit]

Machinima films are, by nature, CGI films.

While computer-generated images of landscapes may be static, computer animation only applies to tướng dynamic images that resemble a movie. However, in general, the term computer animation refers to tướng dynamic images that bởi not allow user interaction, and the term virtual world is used for the interactive animated environments.

Computer animation is essentially a digital successor to tướng the art of stop motion animation of 3 chiều models and frame-by-frame animation of 2 chiều illustrations. Computer generated animations are more controllable phàn nàn other more physically based processes, such as constructing miniatures for effects shots or hiring extras for crowd scenes, and because it allows the creation of images that would not be feasible using any other technology. It can also allow a single graphic artist to tướng produce such nội dung without the use of actors, expensive mix pieces, or props.

To create the illusion of movement, an image is displayed on the computer screen and repeatedly replaced by a new image which is similar to tướng the previous image, but advanced slightly in the time domain name (usually at a rate of 24 or 30 frames/second). This technique is identical to tướng how the illusion of movement is achieved with television and motion pictures.

Text-to-image models[edit]

An image conditioned on the prompt "an astronaut riding a horse, by Hiroshige", generated by Stable Diffusion, a large-scale text-to-image model released in 2022

A text-to-image model is a machine learning model which takes an input natural language mô tả tìm kiếm and produces an image matching that mô tả tìm kiếm. Such models began to tướng be developed in the mid-2010s, as a result of advances in deep neural networks. In 2022, the output of state of the art text-to-image models, such as OpenAI's DALL-E 2, Google Brain's Imagen, StabilityAI's Stable Diffusion, and Midjourney began to tướng approach the quality of real photographs and human-drawn art.

Text-to-image models generally combine a language model, which transforms the input text into a latent representation, and a generative image model, which produces an image conditioned on that representation. The most effective models have generally been trained on massive amounts of image and text data scraped from the trang web.[23]

Virtual worlds[edit]

A yellow submarine in Second Life
Metallic balls created in Blender

A virtual world is an agent-based and simulated environment allowing users to tướng interact with artificially animated characters (e.g software agent) or with other physical users, through the use of avatars. Virtual worlds are intended for its users to tướng inhabit and interact, and the term today has become largely synonymous with interactive 3 chiều virtual environments, where the users take the size of avatars visible to tướng others graphically.[24] These avatars are usually depicted as textual, two-dimensional, or three-dimensional graphical representations, although other forms are possible[25] (auditory[26] and touch sensations for example). Some, but not all, virtual worlds allow for multiple users.

In courtrooms[edit]

Computer-generated imagery has been used in courtrooms, primarily since the early 2000s. However, some experts have argued that it is prejudicial. They are used to tướng help judges or the jury to tướng better visualize the sequence of events, evidence or hypothesis.[27] However, a 1997 study showed that people are poor intuitive physicists and easily influenced by computer generated images.[28] Thus it is important that jurors and other legal decision-makers be made aware that such exhibits are merely a representation of one potential sequence of events.

Broadcast and live events[edit]

Weather visualizations were the first application of CGI in television. It has now become common in weather casting to tướng display full motion đoạn phim of images captured in real-time from multiple cameras and other imaging devices. Coupled with 3 chiều graphics symbols and mapped to tướng a common virtual geospatial model, these animated visualizations constitute the first true application of CGI to tướng TV.

CGI has become common in sports telecasting. Sports and entertainment venues are provided with see-through and overlay nội dung through tracked camera feeds for enhanced viewing by the audience. Examples include the yellow "first down" line seen in television broadcasts of American football games showing the line the offensive team must cross to tướng receive a first down. CGI is also used in association with football and other sporting events to tướng show commercial advertisements overlaid onto the view of the playing area. Sections of rugby fields and cricket pitches also display sponsored images. Swimming telecasts often add a line across the lanes to tướng indicate the position of the current record holder as a race proceeds to tướng allow viewers to tướng compare the current race to tướng the best performance. Other examples include hockey puck tracking and annotations of racing xế hộp performance[29] and snooker ball trajectories.[30][31] Sometimes CGI on TV with correct alignment to tướng the real world has been referred to tướng as augmented reality.


Computer-generated imagery is often used in conjunction with motion-capture to tướng better cover the faults that come with CGI and animation. Computer-generated imagery is limited in its practical application by how realistic it can look. Unrealistic, or badly managed computer-generated imagery can result in the Uncanny Valley effect.[32] This effect refers to tướng the human ability to tướng recognize things that look eerily lượt thích humans, but are slightly off. Such ability is a fault with normal computer-generated imagery which, due to tướng the complex anatomy of the human-body, can often fail to tướng replicate it perfectly. This is where motion-capture comes into play. Artists can use a motion-capture rig to tướng get footage of a human performing an action and then replicate it perfectly with computer-generated imagery sánh that it looks normal.

The lack of anatomically correct digital models contributes to tướng the necessity of motion-capture as it is used with computer-generated imagery. Because computer-generated imagery reflects only the outside, or skin, of the object being rendered, it fails to tướng capture the infinitesimally small interactions between interlocking muscle groups used in fine motor-control, lượt thích speaking. The constant motion of the face as it makes sounds with shaped lips and tongue movement, along with the facial expressions that go along with speaking are difficult to tướng replicate by hand.[33] Motion capture can catch the underlying movement of facial muscles and better replicate the visual that goes along with the audio, lượt thích Josh Brolin's Thanos.

Xem thêm: liên kết cộng hóa trị

See also[edit]



  1. ^ Ozturk, Selen (March 15, 2023). "Vicious Circle: John Whitney and the Military Origins of Early CGI". Bright Lights Film Journal. Retrieved May 11, 2023.
  2. ^ a b c "14 groundbreaking movies that took special effects to tướng new levels".
  3. ^ Halverson, Dave (December 2005). "Anime Reviews: The Professional Golgo 13". Play. No. 48. United States of America. p. 92.
  4. ^ "Last Starfighter sequel is super close to tướng happening, says Gary Whitta". Archived from the original on 2021-08-29. Retrieved 2021-08-29.
  5. ^ a b c Peitgen 2004, pp. 462–466.
  6. ^ Game programming gems 2 by Mark A. DeLoura 2001 ISBN 1-58450-054-9 page 240 [1]
  7. ^ Digital modeling of material appearance by Julie Dorsey, Holly Rushmeier, François X. Sillion 2007 ISBN 0-12-221181-2 page 217
  8. ^ Sondermann 2008, pp. 8–15.
  9. ^ Interactive environments with open-source software: 3 chiều walkthroughs by Wolfgang Höhl, Wolfgang Höhl 2008 ISBN 3-211-79169-8 pages 24-29
  10. ^ "Light: The art of exposure". GarageFarm. 2020-11-12. Retrieved 2020-11-12.
  11. ^ Advances in Computer and Information Sciences and Engineering by Tarek Sobh 2008 ISBN 1-4020-8740-3 pages 136-139
  12. ^ Encyclopedia of Multimedia Technology and Networking, Volume 1 by Margherita Pagani 2005 ISBN 1-59140-561-0 page 1027
  13. ^ Interac storytelling: First Joint International Conference by Ulrike Spierling, Nicolas Szilas 2008 ISBN 3-540-89424-1 pages 114-118
  14. ^ Total Knee Arthroplasty by Johan Bellemans, Michael D. Ries, Jan M.K. Victor 2005 ISBN 3-540-20242-0 pages 241-245
  15. ^ I. Waechter et al. Patient Specific Models for Minimally Invasive Aortic Valve Implantation in Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2010 edited by Tianzi Jiang, 2010 ISBN 3-642-15704-1 pages 526-560
  16. ^ Cloth modeling and animation by Donald House, David E. Breen 2000 ISBN 1-56881-090-3 page 20
  17. ^ Film and photography by Ian Graham 2003 ISBN 0-237-52626-3 page 21
  18. ^ Designing clothes: culture and organization of the fashion industry by Veronica Manlow 2007 ISBN 0-7658-0398-4 page 213
  19. ^ Handbook of Virtual Humans by Nadia Magnenat-Thalmann and Daniel Thalmann, 2004 ISBN 0-470-02316-3 pages 353-370
  20. ^ Mathematical optimization in computer graphics and vision by Luiz Velho, Paulo Cezar Pinto Carvalho 2008 ISBN 0-12-715951-7 page 177
  21. ^ a b c GPU-based interactive visualization techniques by Daniel Weiskopf 2006 ISBN 3-540-33262-6 pages 1-8
  22. ^ Trends in interactive visualization by Elena cầu xin Zudilova-Seinstra, Tony Adriaansen, Robert Liere 2008 ISBN 1-84800-268-8 pages 1-7
  23. ^ Vincent, James (May 24, 2022). "All these images were generated by Google's latest text-to-image AI". The Verge. Vox Media. Retrieved May 28, 2022.
  24. ^ Cook, A.D. (2009). A case study of the manifestations and significance of social presence in a multi-user virtual environment. MEd Thesis. Available online
  25. ^ Biocca & Levy 1995, pp. 40–44.
  26. ^ Begault 1994, p. 212.
  27. ^ Computer-generated images influence trial results The Conversation, 31 October 2013
  28. ^ Kassin, S. M. (1997). "Computer-animated Display and the Jury: Facilitative and Prejudicial Effects". Law and Human Behavior. 40 (3): 269–281. doi:10.1023/a:1024838715221. S2CID 145311101. [2]
  29. ^ Archived at Ghostarchive and the Wayback Machine: Arti AR highlights at SRX -- the first sports augmented reality live from a moving car!, retrieved 2021-07-14
  30. ^ Azuma, Ronald; Balliot, Yohan; Behringer, Reinhold; Feiner, Steven; Julier, Simon; MacIntyre, Blair. Recent Advances in Augmented Reality Computers & Graphics, November 2001.
  31. ^ Marlow, Chris. Hey, hockey puck! NHL PrePlay adds a second-screen experience to tướng live games, digitalmediawire 27 April 2012.
  32. ^ Palomäki, Jussi; Kunnari, Anton; Drosinou, Marianna; Koverola, Mika; Lehtonen, Noora; Halonen, Juho; Repo, Marko; Laakasuo, Michael (2018-11-01). "Evaluating the replicability of the uncanny valley effect". Heliyon. 4 (11): e00939. doi:10.1016/j.heliyon.2018.e00939. ISSN 2405-8440. PMC 6260244. PMID 30519654.
  33. ^ Pelachaud, Catherine; Steedman, Mark; Badler, Norman (1991-06-01). "Linguistic Issues in Facial Animation". Center for Human Modeling and Simulation.


  • Begault, Durand R. (1994). 3-D Sound for Virtual Reality and Multimedia. AP Professional. ISBN 978-0-1208-4735-8.
  • Biocca, Frank; Levy, Mark R. (1995). Communication in the Age of Virtual Reality. Lawrence Erlbaum Associates. ISBN 978-0-8058-1549-8.
  • Peitgen, Heinz-Otto; Jürgens, Hartmut; Saupe, Dietmar (2004). Chaos and Fractals: New Frontiers of Science. Springer Science & Business Media. ISBN 978-0-387-20229-7.
  • Sondermann, Horst (2008). Light Shadow Space: Architectural Rendering with Cinema 4D. Vienna: Springer. ISBN 978-3-211-48761-7.

External links[edit]

  • A Critical History of Computer Graphics and Animation – a course page at Ohio State University that includes all the course materials and extensive supplementary materials (videos, articles, links).
  • CG101: A Computer Graphics Industry Reference ISBN 073570046X Unique and personal histories of early computer graphics production, plus a comprehensive foundation of the industry for all reading levels.
  • F/X Gods, by Anne Thompson, Wired, February 2005.
  • "History Gets A Computer Graphics Make-Over" Tayfun King, Click, Đài truyền hình BBC World News (2004-11-19)
  • NIH Visible Human Gallery