pith. sign in

arxiv: 2605.14835 · v1 · pith:2WNYOV6Tnew · submitted 2026-05-14 · 💻 cs.CY · cs.GR

The Racial Character of Computer Graphics Research

Theodore Kim , Alexa Schor , Julian Posada , Alka V. Menon This is my paper

Pith reviewed 2026-06-30 20:08 UTC · model grok-4.3

classification 💻 cs.CY cs.GR
keywords computer graphicsskin renderinghair simulationracial biasSIGGRAPHACM Transactions on Graphicsalgorithmic fairnesshuman depiction
0
0 comments X

The pith

Computer graphics algorithms for human skin and hair are formulated for white skin and straight hair, not as generic models.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper performs a systematic review of human depiction algorithms published in SIGGRAPH and ACM Transactions on Graphics. It shows that skin rendering methods assume translucent high-albedo materials characteristic of white skin, while hair methods model straight rods and wires. This creates a hierarchy in which white skin mathematics functions as the computational base for all skin types. The authors introduce McDaniels Methods to label algorithms that embed racial hierarchy beneath claims of universality and Durald Methods for those developed through close collaboration with the people depicted. A reader would care because these algorithms underpin imagery in film, games, and virtual environments that reach wide audiences.

Core claim

A systematic review of SIGGRAPH and ACM Transactions on Graphics papers confirms that algorithms claiming generic applicability to human skin are designed for high-albedo translucent materials typical of white skin, and those claiming generic applicability to human hair are designed for rods, wires, and threads analogous to straight hair. The review identifies conceptual binarization in which white skin math serves as the substrate for all skin, and notes that the first examples of computer-generated Type 4 hair appear only after 2020. The paper introduces the labels McDaniels Methods for algorithms that reinforce racial hierarchy under a false cover of diversity and Durald Methods for algor

What carries the argument

The systematic review of skin and hair rendering papers in SIGGRAPH and ACM Transactions on Graphics that uncovers binarization treating white skin math as substrate for all skin, together with the new conceptual labels McDaniels Methods and Durald Methods.

If this is right

  • Skin rendering research must develop models for diverse albedo and translucency values without using white skin math as the base case.
  • Hair simulation research must incorporate explicit support for curly and coily textures rather than treating them as later extensions.
  • Algorithms should be evaluated for embedded racial assumptions instead of being treated as universal by default.
  • Future work should prioritize Durald Methods that involve direct collaboration with the communities being depicted.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same pattern of default assumptions may appear in downstream tools such as AI image generators trained on graphics outputs.
  • Repeating the review on papers published after 2020 would test whether the identified patterns have shifted.
  • Parallel systematic reviews in adjacent fields such as computer vision could reveal comparable default assumptions about human appearance.

Load-bearing premise

The authors' reading of algorithm intent in the selected papers accurately reflects original design goals and the reviewed set represents the broader field without selection effects.

What would settle it

A pre-2020 SIGGRAPH or ACM Transactions on Graphics paper that presents a skin rendering algorithm explicitly formulated for low-albedo high-melanin materials without deriving from white skin physics, or a hair algorithm for Type 4 hair before 2020.

Figures

Figures reproduced from arXiv: 2605.14835 by Alexa Schor, Alka V. Menon, Julian Posada, Theodore Kim.

Figure 1
Figure 1. Figure 1: Left: Percentage of total papers coming form industrial labs in SIGGRAPH and TOG. Film studios like Lucasfilm and Pixar had early influence, as well as Disney in the 2000s and 2010s. Right: Geographic location of authors over time. North America dominated early on, and majority currently skews WEIRD (Western, Educated, Industrialized, Rich, and Democratic). [144] The data source for these figures is descri… view at source ↗
Figure 2
Figure 2. Figure 2: 3D renderings from papers that investigate skin as an optical medium, respectively [ [PITH_FULL_IMAGE:figures/full_fig_p008_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Examples from other papers presenting optical materials that are deemed analogous to “skin”. Alabaster [ [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Examples from papers presenting layered models of skin. In the left pair, swatches of different skin color are presented, [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Examples of Black skin in relighting algorithms, respectively [ [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Inconsistent labels for “curly” hair. From left to right, “curly ponytail” [ [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Two tokenism examples. In the left pair [ [PITH_FULL_IMAGE:figures/full_fig_p014_7.png] view at source ↗
read the original abstract

Computer graphics algorithms for generating photorealistic imagery are widely perceived to be universal, and capable of conjuring anything that a filmmaker or game designer can imagine. However, recent works have suggested that 3D algorithms for depicting synthetic humans are far from generic, and instead favor historically hegemonic characteristics. We present the first systematic review of human depiction in the top computer graphics conference and the journal of record (SIGGRAPH and ACM Transactions on Graphics) that confirms previous hypotheses. Algorithms that claim to be generically rendering "human skin'' are in fact imagined and formulated for translucent, "high albedo" materials such as white skin. Algorithms claiming to apply generically to "human hair" are formulated for "rods", "wires" and "threads" which are analogous to straight hair. Our analysis reveals conceptual binarization, where algorithms for white skin are treated as computational substrate for "all" skin, imposing a hierarchical assumption that all skin descends from the math and physics of white skin. Hair algorithms follow a similar historical pattern, with the first examples of computer-generated Type 4 hair only appearing after the murder of George Floyd in 2020. We offer a new conceptual label, McDaniels Methods, for characterizing and critiquing computer graphics algorithms that reinforce racial hierarchy under a false cover of diversity. We also offer an inverse label, Durald Methods, for algorithms that were closely co-designed with the people being depicted. Our analysis points the way towards several neglected avenues for future research.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

4 major / 1 minor

Summary. The paper presents what it describes as the first systematic review of algorithms for depicting synthetic humans in SIGGRAPH and ACM Transactions on Graphics. It argues that skin-rendering methods claiming generality are in fact formulated for high-albedo, translucent materials characteristic of white skin, while hair-rendering methods are formulated for rod-, wire-, and thread-like structures analogous to straight hair. The analysis identifies a pattern of 'conceptual binarization' in which white-skin mathematics is treated as the computational substrate for all skin, and reports that the first examples of Type 4 hair appear only after 2020. The authors introduce two new labels—'McDaniels Methods' for algorithms that reinforce racial hierarchy under a false cover of diversity and 'Durald Methods' for algorithms co-designed with the people depicted—and conclude by identifying neglected research directions.

Significance. If the review methodology were shown to be exhaustive and the interpretive claims were grounded in explicit technical counter-examples from the source papers, the work would draw attention to an under-examined dimension of graphics research and could usefully prompt re-examination of parameter choices and example selection in rendering literature. The introduction of named categories for critiquing implicit assumptions is a novel framing device, though its utility depends on whether the categories can be applied reproducibly by other readers.

major comments (4)
  1. [Abstract] Abstract and opening paragraphs: the claim to have performed 'the first systematic review' is not accompanied by any statement of search protocol, database queries, inclusion/exclusion criteria, total number of papers examined, or inter-rater reliability measures. Without these details the representativeness of the selected SIGGRAPH/TOG corpus cannot be evaluated and the central empirical claim remains unsupported.
  2. [Abstract] Abstract, paragraph on skin and hair algorithms: the inference that algorithms 'claiming to be generically rendering human skin' were 'imagined and formulated for' white skin rests on the authors' reading of parameter choices and early examples rather than on any demonstration that the original papers stated or assumed racial specificity. This interpretive step is load-bearing for the binarization thesis yet is presented without direct quotation or technical counter-example from the reviewed works.
  3. [Abstract] Abstract, hair timeline claim: the assertion that 'the first examples of computer-generated Type 4 hair only appearing after the murder of George Floyd in 2020' requires a specific citation list or table showing the publication dates and hair-type coverage of all reviewed hair papers; absent such evidence the chronological claim cannot be verified and risks post-hoc framing.
  4. [Abstract] Abstract, new conceptual labels: 'McDaniels Methods' and 'Durald Methods' are defined by applying the authors' own interpretive categories back to the same corpus from which the categories were derived. This circular construction is acknowledged in the reader's circularity score and weakens the analytical framework unless an independent validation set or external coding protocol is supplied.
minor comments (1)
  1. [Abstract] The abstract uses scare quotes around 'human skin' and 'human hair' without first defining the precise technical scope the authors attribute to those phrases in the source literature.

Simulated Author's Rebuttal

4 responses · 0 unresolved

We thank the referee for their detailed and constructive comments. We address each major comment point by point below, indicating where we will revise the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract and opening paragraphs: the claim to have performed 'the first systematic review' is not accompanied by any statement of search protocol, database queries, inclusion/exclusion criteria, total number of papers examined, or inter-rater reliability measures. Without these details the representativeness of the selected SIGGRAPH/TOG corpus cannot be evaluated and the central empirical claim remains unsupported.

    Authors: We agree that the abstract and opening paragraphs should explicitly state the search protocol, database queries, inclusion/exclusion criteria, total number of papers examined, and any reliability measures to support the systematic review claim. The full manuscript describes the corpus in the methods section, but we will revise the abstract and introduction to include these details. revision: yes

  2. Referee: [Abstract] Abstract, paragraph on skin and hair algorithms: the inference that algorithms 'claiming to be generically rendering human skin' were 'imagined and formulated for' white skin rests on the authors' reading of parameter choices and early examples rather than on any demonstration that the original papers stated or assumed racial specificity. This interpretive step is load-bearing for the binarization thesis yet is presented without direct quotation or technical counter-example from the reviewed works.

    Authors: The inference draws from the specific parameter ranges (e.g., albedo and translucency values) and example imagery in the source papers, which align with high-albedo light skin characteristics. We will add explicit technical counter-examples and direct quotations from the reviewed works to better ground this analysis in the revised manuscript. revision: partial

  3. Referee: [Abstract] Abstract, hair timeline claim: the assertion that 'the first examples of computer-generated Type 4 hair only appearing after the murder of George Floyd in 2020' requires a specific citation list or table showing the publication dates and hair-type coverage of all reviewed hair papers; absent such evidence the chronological claim cannot be verified and risks post-hoc framing.

    Authors: We agree that a table or list of reviewed hair papers with publication dates and hair-type coverage is needed to verify the timeline. We will include this in the revised manuscript. revision: yes

  4. Referee: [Abstract] Abstract, new conceptual labels: 'McDaniels Methods' and 'Durald Methods' are defined by applying the authors' own interpretive categories back to the same corpus from which the categories were derived. This circular construction is acknowledged in the reader's circularity score and weakens the analytical framework unless an independent validation set or external coding protocol is supplied.

    Authors: The labels are conceptual tools derived from observed patterns to enable critique of assumptions in the literature. We will revise the definitions section to clarify their scope and provide guidance for application beyond the current corpus. revision: partial

Circularity Check

0 steps flagged

No significant circularity; interpretive review with independent external inputs.

full rationale

This is a literature review paper whose claims rest on close reading of external SIGGRAPH/TOG publications rather than any derivation, equation, fitted parameter, or self-referential prediction. The new labels McDaniels Methods and Durald Methods are outputs of the analysis, not inputs that force the classification of the reviewed papers. No self-citation chains, uniqueness theorems, or ansatzes appear in the abstract or described structure. The central interpretive steps (algorithm scope, historical timing, binarization) are presented as conclusions drawn from the cited corpus, not as tautologies that reduce to the paper's own definitions by construction. This meets the default expectation of a non-circular analysis.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 2 invented entities

The central claim rests on the interpretive premise that algorithms labeled 'generic' were intended to cover all humans yet were formulated around specific racial characteristics; the paper also introduces two new named categories without external validation.

axioms (1)
  • domain assumption Algorithms described as generic for human skin or hair are intended to apply universally but instead encode assumptions favoring historically hegemonic traits.
    This premise is required to interpret the reviewed algorithms as reinforcing racial hierarchy rather than as neutral technical choices.
invented entities (2)
  • McDaniels Methods no independent evidence
    purpose: Label for computer graphics algorithms that reinforce racial hierarchy while claiming diversity or universality.
    New conceptual category introduced by the authors to characterize the reviewed work.
  • Durald Methods no independent evidence
    purpose: Label for algorithms closely co-designed with the people being depicted.
    New conceptual category introduced by the authors as an inverse to McDaniels Methods.

pith-pipeline@v0.9.1-grok · 5802 in / 1408 out tokens · 33058 ms · 2026-06-30T20:08:47.747421+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

300 extracted references · 11 canonical work pages

  1. [1]

    2006.Artificial knowing: Gender and the thinking machine

    Alison Adam. 2006.Artificial knowing: Gender and the thinking machine. Routledge

    2006

  2. [2]

    Abby Aguirre. 2020. Simone Biles on Overcoming Abuse, the Postponed Olympics, and Training During a Pandemic.Vogue(2020)

    2020

  3. [3]

    Matt Aitken, Greg Butler, Dan Lemmon, Eric Saindon, Dana Peters, and Guy Williams. 2004. The Lord of the Rings: the visual effects that brought middle earth to the screen. InACM SIGGRAPH Courses. 11–es

    2004

  4. [4]

    O Alexander, M Rogers, W Lambeth, J Chiang, W Ma, C Wang, and P Debevec. 2009. The digital emily project: Achieving a photoreal digital actor.IEEE Computer Graphics and Applications30 (2009)

    2009

  5. [5]

    Carlos Aliaga, Mengqi Xia, Hao Xie, Adrian Jarabo, Gustav Braun, and Christophe Hery. 2023. A Hyperspectral Space of Skin Tones for Inverse Rendering of Biophysical Skin Properties.Computer Graphics Forum(2023). doi:10.1111/cgf.14887

    work page doi:10.1111/cgf.14887 2023

  6. [6]

    1949.Painting with light

    John Alton. 1949.Painting with light. Macmillan. The Racial Character of Computer Graphics Research FAccT ’26, June 25–28, 2026, Montreal, QC, Canada

    1949

  7. [7]

    Shivangi Aneja, Justus Thies, Angela Dai, and Matthias Nießner. 2023. Clipface: Text-guided editing of textured 3d morphable models. InACM SIGGRAPH 2023 Conference Proceedings. 1–11

    2023

  8. [8]

    Ken-ichi Anjyo, Yoshiaki Usami, and Tsuneya Kurihara. 1992. A simple method for extracting the natural beauty of hair. InProceedings of SIGGRAPH. 111–120

    1992

  9. [9]

    Jonghee Back, Binh-Son Hua, Toshiya Hachisuka, and Bochang Moon. 2022. Self-supervised post-correction for Monte Carlo denoising. InACM SIGGRAPH 2022 Conference Proceedings. 1–8

    2022

  10. [10]

    Kelian Baert, Shrisha Bharadwaj, Fabien Castan, Benoit Maujean, Marc Christie, Victoria Abrevaya, and Adnane Boukhayma. 2024. SPARK: Self-supervised Personalized Real-time Monocular Face Capture. InSIGGRAPH Asia 2024 Conference Papers(Tokyo, Japan)(SA ’24). Association for Computing Machinery, New York, NY, USA, Article 113, 12 pages. doi:10.1145/3680528.3687704

    work page doi:10.1145/3680528.3687704 2024

  11. [11]

    Shaojie Bai, Te-Li Wang, Chenghui Li, Akshay Venkatesh, Tomas Simon, Chen Cao, Gabriel Schwartz, Jason Saragih, Yaser Sheikh, and Shih-En Wei. 2024. Universal Facial Encoding of Codec Avatars from VR Headsets.ACM Trans. Graph. (TOG)43, 4 (2024), 1–22

    2024

  12. [12]

    Arthur E Balbao and Marcelo Walter. 2022. A Biologically Inspired Hair Aging Model.ACM Trans. Graph. (TOG)41, 6 (2022), 1–9

    2022

  13. [13]

    Brent Bambury. 2025. Realistic animation of Black hair has lagged far behind other hair types for years. This artist has a plan for how to fix that.CBC, Day 6(2025)

    2025

  14. [14]

    David C Banks. 1994. Illumination in diverse codimensions. InProceedings of the 21st annual conference on Computer graphics and interactive techniques. 327–334

    1994

  15. [15]

    Linchao Bao, Xiangkai Lin, Yajing Chen, Haoxian Zhang, Sheng Wang, Xuefei Zhe, Di Kang, Haozhi Huang, Xinwei Jiang, Jue Wang, et al. 2021. High-fidelity 3d digital human head creation from rgb-d selfies.ACM Trans. Graph. (TOG)41, 1 (2021), 1–21

    2021

  16. [16]

    David Baraff and Andrew Witkin. 1998. Large steps in cloth simulation. InProceedings of SIGGRAPH. 43–54

    1998

  17. [17]

    Rasmus Barringer and Tomas Akenine-Möller. 2013. A4: asynchronous adaptive anti-aliasing using shared memory.ACM Trans. Graph. (TOG)32, 4 (2013), 1–10

    2013

  18. [18]

    Rasmus Barringer, Carl Johan Gribel, and Tomas Akenine-Möller. 2012. High-quality curve rendering using line sampled visibility. ACM Trans. Graph. (TOG)31, 6 (2012), 1–10

    2012

  19. [19]

    Christopher Batty, Andres Uribe, Basile Audoly, and Eitan Grinspun. 2012. Discrete viscous sheets.ACM Trans. Graph. (TOG)31, 4 (2012), 1–7

    2012

  20. [20]

    Thabo Beeler, Bernd Bickel, Paul Beardsley, Bob Sumner, and Markus Gross. 2010. High-quality single-shot capture of facial geometry. ACM Trans. Graph.29, 4 (2010), 1–9

    2010

  21. [21]

    Thabo Beeler, Bernd Bickel, Gioacchino Noris, Paul Beardsley, Steve Marschner, Robert W Sumner, and Markus Gross. 2012. Coupled 3D reconstruction of sparse facial hair and skin.ACM Trans. Graph. (ToG)31, 4 (2012), 1–10

    2012

  22. [22]

    Thabo Beeler and Derek Bradley. 2014. Rigid stabilization of facial expressions.ACM Trans. Graph. (TOG)33, 4 (2014), 1–9

    2014

  23. [23]

    Thabo Beeler, Fabian Hahn, Derek Bradley, Bernd Bickel, Paul A Beardsley, Craig Gotsman, Robert W Sumner, and Markus H Gross

  24. [24]

    Graph.30, 4 (2011), 75

    High-quality passive facial performance capture using anchor frames.ACM Trans. Graph.30, 4 (2011), 75

    2011

  25. [25]

    2019.Race After Technology: Abolitionist Tools for the New Jim Code

    Ruha Benjamin. 2019.Race After Technology: Abolitionist Tools for the New Jim Code. John Wiley & Sons

    2019

  26. [26]

    Miklós Bergou, Basile Audoly, Etienne Vouga, Max Wardetzky, and Eitan Grinspun. 2010. Discrete viscous threads.ACM Trans. Graph. (TOG)29, 4 (2010), 1–10

    2010

  27. [27]

    Miklós Bergou, Max Wardetzky, Stephen Robinson, Basile Audoly, and Eitan Grinspun. 2008. Discrete Elastic Rods.ACM Trans. Graph. 27, 3 (aug 2008), 63:1–63:12

    2008

  28. [28]

    Amit Bermano, Thabo Beeler, Yeara Kozlov, Derek Bradley, Bernd Bickel, and Markus Gross. 2015. Detailed spatio-temporal recon- struction of eyelids.ACM Trans. Graph. (TOG)34, 4 (2015), 1–11

    2015

  29. [29]

    Amit Bermano, Philipp Brüschweiler, Anselm Grundhöfer, Daisuke Iwai, Bernd Bickel, and Markus Gross. 2013. Augmenting physical avatars using projector-based illumination.ACM Trans. Graph. (TOG)32, 6 (2013), 1–10

    2013

  30. [30]

    Amit H Bermano, Derek Bradley, Thabo Beeler, Fabio Zund, Derek Nowrouzezahrai, Ilya Baran, Olga Sorkine-Hornung, Hanspeter Pfister, Robert W Sumner, Bernd Bickel, et al. 2014. Facial performance enhancement using dynamic shape space analysis.ACM Trans. Graph. (TOG)33, 2 (2014), 1–12

    2014

  31. [31]

    Florence Bertails, Basile Audoly, Marie-Paule Cani, Bernard Querleux, Frédéric Leroy, and Jean-Luc Lévêque. 2006. Super-helices for predicting the dynamics of natural hair.ACM Trans. Graph.25, 3 (jul 2006), 1180–1187

    2006

  32. [32]

    Florence Bertails, Basile Audoly, Bernard Querleux, Frédéric Leroy, Jean-Luc Lévêque, and Marie-Paule Cani. 2005. Predicting natural hair shapes by solving the statics of flexible rods. InEurographics short papers. Eurographics

    2005

  33. [33]

    Florence Bertails-Descoubes, Florent Cadoux, Gilles Daviet, and Vincent Acary. 2011. A nonsmooth Newton solver for capturing exact Coulomb friction in fiber assemblies.ACM Trans. Graph. (TOG)30, 1 (2011), 1–14

    2011

  34. [34]

    Shrisha Bharadwaj, Yufeng Zheng, Otmar Hilliges, Michael J Black, and Victoria Fernández Abrevaya. 2023. FLARE: Fast Learning of Animatable and Relightable Mesh Avatars.ACM Trans. Graph.42, 6 (2023), 204

    2023

  35. [35]

    Gaurav Bhokare, Eisen Montalvo, Elie Diaz, and Cem Yuksel. 2024. Real-time hair rendering with hair meshes. InProceedings of SIGGRAPH. 1–10. FAccT ’26, June 25–28, 2026, Montreal, QC, Canada Kim et al

    2024

  36. [36]

    Sai Bi, Stephen Lombardi, Shunsuke Saito, Tomas Simon, Shih-En Wei, Kevyn Mcphail, Ravi Ramamoorthi, Yaser Sheikh, and Jason Saragih. 2021. Deep relightable appearance models for animatable faces.ACM Trans. Graph. (ToG)40, 4 (2021), 1–15

    2021

  37. [37]

    Bernd Bickel, Mario Botsch, Roland Angst, Wojciech Matusik, Miguel Otaduy, Hanspeter Pfister, and Markus Gross. 2007. Multi-scale capture of facial geometry and motion.ACM Trans. Graph. (TOG)26, 3 (2007), 33–es

    2007

  38. [38]

    Bernd Bickel, Peter Kaufmann, Mélina Skouras, Bernhard Thomaszewski, Derek Bradley, Thabo Beeler, Phil Jackson, Steve Marschner, Wojciech Matusik, and Markus Gross. 2012. Physical face cloning.ACM Trans. Graph. (TOG)31, 4 (2012), 1–10

    2012

  39. [39]

    Abeba Birhane, Pratyusha Kalluri, Dallas Card, William Agnew, Ravit Dotan, and Michelle Bao. 2022. The values encoded in machine learning research. InProceedings of the 2022 ACM conference on fairness, accountability, and transparency. 173–184

    2022

  40. [40]

    James F Blinn. 1982. Light reflection functions for simulation of clouds and dusty surfaces.Proceedings of SIGGRAPH16, 3 (1982), 21–29

    1982

  41. [41]

    Eduardo Bonilla-Silva. 2004. From bi-racial to tri-racial: Towards a new system of racial stratification in the USA.Ethnic and racial studies27, 6 (2004), 931–950

    2004

  42. [42]

    2017.Racism without Racists: Color-Blind Racism and the Persistence of Racial Inequality in America(6th ed.)

    Eduardo Bonilla-Silva. 2017.Racism without Racists: Color-Blind Racism and the Persistence of Racial Inequality in America(6th ed.). Rowman & Littlefield, Lanham, MD

    2017

  43. [43]

    2000.Sorting things out: Classification and its consequences

    Geoffrey C Bowker and Susan Leigh Star. 2000.Sorting things out: Classification and its consequences. MIT press

    2000

  44. [44]

    Derek Bradley, Wolfgang Heidrich, Tiberiu Popa, and Alla Sheffer. 2010. High resolution passive facial performance capture.ACM Trans. Graph.29, 4 (2010), 41

    2010

  45. [45]

    Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology.Qualitative research in psychology3, 2 (2006), 77–101

    2006

  46. [46]

    Alan Brunton, Can Ates Arikan, Tejas Madan Tanksale, and Philipp Urban. 2018. 3D printing spatially varying color and translucency. ACM Trans. Graph. (TOG)37, 4 (2018), 1–13

    2018

  47. [47]

    Marcel C Buehler, Gengyan Li, Erroll Wood, Leonhard Helminger, Xu Chen, Tanmay Shah, Daoye Wang, Stephan Garbin, Sergio Orts-Escolano, Otmar Hilliges, et al. 2024. Cafca: High-quality novel view synthesis of expressive faces from casual few-shot captures. InSIGGRAPH Asia 2024 Conference Papers. 1–12

    2024

  48. [48]

    Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency. PMLR, 77–91

    2018

  49. [49]

    Brent Burley, David Adler, Matt Jen-Yuan Chiang, Hank Driskill, Ralf Habel, Patrick Kelly, Peter Kutz, Yining Karl Li, and Daniel Teece

  50. [50]

    The design and evolution of disney’s hyperion renderer.ACM Trans. Graph. (TOG)37, 3 (2018), 1–22

    2018

  51. [51]

    Chen Cao, Vasu Agrawal, Fernando De La Torre, Lele Chen, Jason Saragih, Tomas Simon, and Yaser Sheikh. 2021. Real-time 3D neural facial animation from binocular video.ACM Trans. Graph. (TOG)40, 4 (2021), 1–17

    2021

  52. [52]

    Chen Cao, Derek Bradley, Kun Zhou, and Thabo Beeler. 2015. Real-time high-fidelity facial performance capture.ACM Trans. Graph. (ToG)34, 4 (2015), 1–9

    2015

  53. [53]

    Chen Cao, Menglei Chai, Oliver Woodford, and Linjie Luo. 2018. Stabilized real-time face tracking via a learned dynamic rigidity prior. ACM Trans. Graph. (TOG)37, 6 (2018), 1–11

    2018

  54. [54]

    Chen Cao, Tomas Simon, Jin Kyu Kim, Gabe Schwartz, Michael Zollhoefer, Shunsuke Saito, Stephen Lombardi, Shih-En Wei, Danielle Belko, Shoou-I Yu, et al. 2022. Authentic volumetric avatars from a phone scan.ACM Trans. Graph. (TOG)41, 4 (2022), 1–19

    2022

  55. [55]

    Chen Cao, Hongzhi Wu, Yanlin Weng, Tianjia Shao, and Kun Zhou. 2016. Real-time facial animation with image-based dynamic avatars. ACM Trans. Graph.35, 4 (2016)

    2016

  56. [56]

    Edoardo Carra and Fabio Pellacini. 2019. SceneGit: a practical system for diffing and merging 3D environments.ACM Trans. Graph. (TOG)38, 6 (2019), 1–15

    2019

  57. [57]

    Romain Casati and Florence Bertails-Descoubes. 2013. Super space clothoids.ACM Trans. Graph. (TOG)32, 4 (2013), 1–12

    2013

  58. [58]

    Menglei Chai, Linjie Luo, Kalyan Sunkavalli, Nathan Carr, Sunil Hadap, and Kun Zhou. 2015. High-quality hair modeling from a single portrait photo.ACM Trans. Graph.34, 6 (2015), 204–1

    2015

  59. [59]

    Menglei Chai, Tianjia Shao, Hongzhi Wu, Yanlin Weng, and Kun Zhou. 2016. AutoHair: fully automatic hair modeling from a single image.ACM Trans. Graph., Article 116 (July 2016), 12 pages

    2016

  60. [60]

    Menglei Chai, Lvdi Wang, Yanlin Weng, Yizhou Yu, Baining Guo, and Kun Zhou. 2012. Single-view hair modeling for portrait manipulation.ACM Trans. Graph. (TOG)31, 4 (2012), 1–8

    2012

  61. [61]

    Menglei Chai, Changxi Zheng, and Kun Zhou. 2014. A reduced model for interactive hairs.ACM Trans. Graph. (TOG)33, 4 (2014), 1–11

    2014

  62. [62]

    Prashanth Chandran, Sebastian Winberg, Gaspard Zoss, Jérémy Riviere, Markus Gross, Paulo Gotardo, and Derek Bradley. 2021. Rendering with style: combining traditional and neural approaches for high-quality face rendering.ACM Trans. Graph. (ToG)40, 6 (2021), 1–14

    2021

  63. [63]

    Tenn F Chen, Gladimir VG Baranoski, Bradley W Kimmel, and Erik Miranda. 2015. Hyperspectral modeling of skin appearance.ACM Trans. Graph. (TOG)34, 3 (2015), 1–14

    2015

  64. [64]

    Xiao-Song Chen, Chen-Feng Li, Geng-Chen Cao, Yun-Tao Jiang, and Shi-Min Hu. 2020. A moving least square reproducing kernel particle method for unified multiphase continuum simulation.ACM Trans. Graph. (TOG)39, 6 (2020), 1–15. The Racial Character of Computer Graphics Research FAccT ’26, June 25–28, 2026, Montreal, QC, Canada

    2020

  65. [65]

    Yufan Chen, Lizhen Wang, Qijing Li, Hongjiang Xiao, Shengping Zhang, Hongxun Yao, and Yebin Liu. 2024. Monogaussianavatar: Monocular gaussian point-based head avatar. InACM SIGGRAPH 2024 Conference Papers. 1–9

    2024

  66. [66]

    Per Christensen, Julian Fong, Jonathan Shade, Wayne Wooten, Brenden Schubert, Andrew Kensler, Stephen Friedman, Charlie Kilpatrick, Cliff Ramshaw, Marc Bannister, et al. 2018. Renderman: An advanced path-tracing architecture for movie rendering.ACM Trans. Graph. (TOG)37, 3 (2018), 1–21

    2018

  67. [67]

    Nelson S-H Chu and Chiew-Lan Tai. 2005. Moxi: real-time ink dispersion in absorbent paper.ACM Trans. Graph. (TOG)24, 3 (2005), 504–511

    2005

  68. [68]

    Robert L Cook, John Halstead, Maxwell Planck, and David Ryu. 2007. Stochastic simplification of aggregate detail.ACM Trans. Graph. (TOG)26, 3 (2007), 79–es

    2007

  69. [69]

    2019.Thick: And other essays

    Tressie McMillan Cottom. 2019.Thick: And other essays. The New Press

    2019

  70. [70]

    Kate Crawford and Trevor Paglen. 2021. Excavating AI: The politics of images in machine learning training sets.Ai & Society36, 4 (2021), 1105–1116

    2021

  71. [71]

    2019.Seeing race again: Countering colorblindness across the disciplines

    Kimberlé Williams Crenshaw, Luke Charles Harris, Daniel Martinez HoSang, and George Lipsitz. 2019.Seeing race again: Countering colorblindness across the disciplines. Univ of California Press

    2019

  72. [72]

    Octave Crespel, Emile Hohnadel, Thibaut Métivet, and Florence Bertails-Descoubes. 2024. Contact detection between curved fibres: high order makes a difference. InProceedings of SIGGRAPH

    2024

  73. [73]

    2014.Hair Type Chart: How to Find Your Curl Pattern with Pictures

    CurlCentric. 2014.Hair Type Chart: How to Find Your Curl Pattern with Pictures. https://www.curlcentric.com/hair-typing-system/

    2014

  74. [74]

    Darke, Isaac Olander, and Theodore Kim

    A.M. Darke, Isaac Olander, and Theodore Kim. 2024. More Than Killmonger Locs: A Style Guide for Black Hair (in Computer Graphics). InACM SIGGRAPH Courses(Denver, CO, USA)(SIGGRAPH Courses). Article 18, 251 pages

    2024

  75. [75]

    Gilles Daviet. 2020. Simple and scalable frictional contacts for thin nodal objects.ACM Trans. Graph.39, 4 (2020), 61–1

    2020

  76. [76]

    Gilles Daviet. 2023. Interactive Hair Simulation on the GPU using ADMM. InProceeindgs of SIGGRAPH. 1–11

    2023

  77. [77]

    Gilles Daviet, Florence Bertails-Descoubes, and Laurence Boissieux. 2011. A hybrid iterative solver for robustly capturing coulomb friction in hair dynamics.ACM Trans. Graph.30, 6 (2011), 1–12

    2011

  78. [78]

    Edilson de Aguiar, Carsten Stoll, Christian Theobalt, Naveed Ahmed, Hans-Peter Seidel, and Sebastian Thrun. 2008. Performance capture from sparse multi-view video.ACM Trans. Graph.27, 3 (2008), 1–10

    2008

  79. [79]

    De La Mettrie, D

    R. De La Mettrie, D. Saint-Léger, G. Loussouarn, A. Garcel, C. Porter, and A. Langaney. 2007. Shape variability and classification of human hair: a worldwide approach.Human biology79, 3 (2007), 265–281

    2007

  80. [80]

    Paul Debevec, Tim Hawkins, Chris Tchou, Haarm-Pieter Duiker, Westley Sarokin, and Mark Sagar. 2000. Acquiring the reflectance field of a human face. InProceedings of SIGGRAPH. 145–156

    2000

Showing first 80 references.