(推奨)アブス卜投稿 April 19, 2021, 23:59 UTC
論文投稿 April 24, 2021, 23:59 UTC
採択通知 June 7, 2021
修正締切 June 18, 2021, 23:59 UTC
カメラレディ締切 June 25, 2021, 23:59 UTC
チュートリアル July 10-11, 2021
カンファレンス July 12–14, 2021

Call For Technical Papers

We invite submissions related to, but not limited to, the following topics:


  • 三次元復元(Acquisition and reconstruction)
  • 3Dプリンティング(Analysis and fabrication for 3D printing)
  • 建築の幾何学(Architectural geometry)
  • 離散微分幾何学(Discrete differential geometry)
  • 三次元幾何の探索(Exploration of shape collections)
  • 幾何データの表現(Geometry and topology representations)
  • 幾何データの圧縮(Geometry compression)
  • 幾何学と深層学習(Geometric deep learning)
  • 幾何形状処理の応用(Geometry processing applications)
  • インタラクティブな応用(Interactive techniques)
  • メッシュ生成・再メッシュ(Meshing and remeshing)
  • マルチスケールモデリング(Multiresolution modeling)
  • マルチモーダル形状処理(Multimodal shape processing)
  • 大規模形状処理(Processing of massive geometric datasets)
  • 機械学習における幾何データの表現(Geometric representations for machine learning)
  • 幾何形状解析・生成(Shape analysis and synthesis)
  • シミュレーション・アニメーション(Simulation and animation)
  • フィルタリング(Smoothing, filtering, and denoising)
  • 幾何データの変形や座標マッピング(Surface and volume parameterization and deformation)


今年から初めて、SGPではデータセット論文を受け付けています。幾何データのデータセットは幾何形状処理の 長期的な発展に必要不可欠で、特に最近は機械学習や深層学習の台頭により重要性が増しています。 SGPでは大規模で複雑なデータセットを作り、ドキュメントし、解析する論文を募集しています。


新規性 今までには無い新しい要素を含んでいる、有用なラベル付けがされている、 現時点で存在しているデータセットよりも大規模である、新しい問題を提起されている、等。

インパクト データセットの存在意義、将来的なポテンシャル、分野の 未来への影響、等。

プレゼンテーション 存在意義や問題提起が明確に伝わっているか、データの使用に関するドキュメンテーションが 充実しているか、実験は充実していてかつ説得力があるか、等。

アクセシビリティ 計算資源やリソースが少ないユーザーでも使う事ができるか、オープンなデータフォーマットが使われているか、 データを解析するためのツールが備わっているか、データは何処にホストされているか、ライセンスはなにか、 特許やIPに関する制約はあるか、等。

プライバシーと倫理 データセットにプライバシーに関わるデータを含んでいるか、倫理に関する議論がされているか、データの悪用についての 対策や議論がされているか、等。


  • The Princeton Shape Benchmark paper dataset

  • Thingi10K: A Dataset of 10000 3D-Printing Models paper dataset

  • ABC: A Big CAD Model Dataset For Geometric Deep Learning paper dataset

  • ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes paper dataset

  • The Digital Michelangelo Project: 3D Scanning of Large Statues paper dataset


Please format your article using the template for SGP available on the SRMv2 website: https://srmv2.eg.org. SGP 2021 does not impose a strict maximum length for submitted papers. However, Computer Graphics Forum and SGP 2021 recommend that research papers be up to 10 pages (including all images, but excluding references). Papers should only be as long as their content would justify. Reviewers might rate a submission lower if it is perceived as being unnecessarily long. Authors are encouraged to use supplementary documents to provide extra content.


Review is based on a dual-anonymous reviewing process: submission authors do not know the identity of their reviewers and reviewers do not know the identity of submission authors (or each other). All submitted papers must be anonymized. Please be sure to remove all personal data (such as authors, affiliations, etc.) from your submission. References to your own work should be made in the third person. Reviewers are asked to keep confidentiality on all materials sent to them for evaluation.

Submitting your article

Articles must be submitted, in electronic pdf format, using the Submission and Review Management (SRMv2) system.

In order for a paper to be considered for publication, a corresponding abstract must be submitted. Although the abstract submission deadline (see timeline above) is not mandatory and will not prevent a full paper submission, it is strongly encouraged to abide by it, to help assign relevant reviewers (paper bidding done on the abstract provided by the abstract deadline).

Reviewing process

Submitted papers undergo a two-stage review process, involving dual-anonymous assessment by carefully selected reviewers from the technical papers committee. Articles are conditionally accepted after the first round. Final acceptance is determined in the second round, based on the revised version of the article.

Anonymity and Preprints

For the first time this year, we are adopting the same policy as SIGGRAPH (which is similar to CVPR) on preprints, including those shared via arXiv. Following this policy almost verbatim, we recognize that prepublications and talks have become part of the scientific discourse, and SGP allows these means of communication. Specifically, before the final acceptance decision is made:

  • Authors must not discuss the research described in submitted SGP papers with the media. Media includes editors/journalists/writers/interviewers of newspapers, radio, television, magazines, as well as public relations and media arms of companies, universities, and other research institutions.
  • After submitting to SGP, authors may archive the submission without mentioning SGP as an institutional tech report or on arXiv or a similar service.
  • Authors must not make any posts to social media or elsewhere that can be linked to a specific SGP submission (e.g., mentioning the title of the submission or details and content and saying that it is a SGP submission).
  • Authors may talk about their work in a presentation without saying it is submitted to SGP.
  • Authors may mention their submission(s) as under review at SGP as part of the written materials submitted for job and funding applications. Authors may talk about the research involved in their submission in talks given for these purposes as well, without mentioning SGP.


Accepted papers will be published in a regular issue of Computer Graphics Forum, the International Journal of the EUROGRAPHICS Association. Computer Graphics Forum (Print ISSN: 0167-7055; Online ISSN: 1467-8659) is the official journal of Eurographics, published in cooperation with Wiley-Blackwell, and is one of the leading journals for researchers, developers and users of Computer Graphics in both commercial and academic environment. It has one of the highest impact factors in the field, and it is indexed by all major databases; additionally, the electronic version of all accepted work will also be indexed and accessible by the EG Digital Library.