Opendata, web and dolomites


Interpreting Drawings for 3D Design

Total Cost €


EC-Contrib. €






 D3 project word cloud

Explore the words cloud of the D3 project. It provides you a very rough idea of what is the project "D3" about.

tighten    provides    techniques    understand    ill    feedback    extensively    synthetic    create    indicating    cast    point    draw    originality    inverse    satisfies    shape    engineering    anywhere    machine    first    designers    viewers    single    configurations    suitable    finalized    lie    power    model    derive    continuous    data    exploration    professional    rigidity    prototyping    modeling    input    significantly    computers    simulation    constraint    optimization    interpret    image    learning    approximate    creative    computer    drawing    visceral    variables    externalize    train    printing    automatically    leverage    geometric    impractical    limited    discrete    drawings    clashes    synthesize    constraints    estimating    ambition    3d    joint    idea    ideas    feasibility    interpretable    reconstruction    nature    predict    models    tackling    formalize    communicate    representing    shapes    physical    tools    algorithms    technique    rapid    solutions    tediousness    posed   

Project "D3" data sheet

The following table provides information about the project.


Organization address
postcode: 78153

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country France [FR]
 Total cost 1˙482˙761 €
 EC max contribution 1˙482˙761 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2016-STG
 Funding Scheme ERC-STG
 Starting year 2017
 Duration (year-month-day) from 2017-02-01   to  2022-01-31


Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 


 Project objective

Designers draw extensively to externalize their ideas and communicate with others. However, drawings are currently not directly interpretable by computers. To test their ideas against physical reality, designers have to create 3D models suitable for simulation and 3D printing. However, the visceral and approximate nature of drawing clashes with the tediousness and rigidity of 3D modeling. As a result, designers only model finalized concepts, and have no feedback on feasibility during creative exploration. Our ambition is to bring the power of 3D engineering tools to the creative phase of design by automatically estimating 3D models from drawings. However, this problem is ill-posed: a point in the drawing can lie anywhere in depth. Existing solutions are limited to simple shapes, or require user input to “explain” to the computer how to interpret the drawing. Our originality is to exploit professional drawing techniques that designers developed to communicate shape most efficiently. Each technique provides geometric constraints that help viewers understand drawings, and that we shall leverage for 3D reconstruction. Our first challenge is to formalize common drawing techniques and derive how they constrain 3D shape. Our second challenge is to identify which techniques are used in a drawing. We cast this problem as the joint optimization of discrete variables indicating which constraints apply, and continuous variables representing the 3D model that best satisfies these constraints. But evaluating all constraint configurations is impractical. To solve this inverse problem, we will first develop forward algorithms that synthesize drawings from 3D models. Our idea is to use this synthetic data to train machine learning algorithms that predict the likelihood that constraints apply in a given drawing. In addition to tackling the long-standing problem of single-image 3D reconstruction, our research will significantly tighten design and engineering for rapid prototyping.


List of deliverables.
Data Management Plan Open Research Data Pilot 2019-05-31 11:58:51

Take a look to the deliverables list in detail:  detailed list of D3 deliverables.


year authors and title journal last update
List of publications.
2019 Yulia Gryaditskaya, Mark Sypesteyn, Jan Willem Hoftijzer, Sylvia Pont, Frédo Durand, Adrien Bousseau
published pages: 1-16, ISSN: 0730-0301, DOI: 10.1145/3355089.3356533
ACM Transactions on Graphics (TOG) 38/6 2020-03-05
2019 G. Nishida, A. Bousseau, D. G. Aliaga
Multi‐Pose Interactive Linkage Design
published pages: 277-289, ISSN: 0167-7055, DOI: 10.1111/cgf.13637
Computer Graphics Forum 38/2 2019-08-30
2019 Jean-Dominique Favreau, Florent Lafarge, Adrien Bousseau, Alex Auvolat
Extracting Geometric Structures in Images with Delaunay Point Processes
published pages: 1-1, ISSN: 0162-8828, DOI: 10.1109/tpami.2018.2890586
IEEE Transactions on Pattern Analysis and Machine Intelligence 2019-08-30
2019 Johanna Delanoy, David Coeurjolly, Jacques-Olivier Lachaud, Adrien Bousseau
Combining voxel and normal predictions for multi-view 3D sketching
published pages: 65-72, ISSN: 0097-8493, DOI: 10.1016/j.cag.2019.05.024
Computers & Graphics 82 2019-08-30
2018 Johanna Delanoy, Mathieu Aubry, Phillip Isola, Alexei A. Efros, Adrien Bousseau
3D Sketching using Multi-View Deep Volumetric Prediction
published pages: 1-22, ISSN: 2577-6193, DOI: 10.1145/3203197
Proceedings of the ACM on Computer Graphics and Interactive Techniques 1/1 2019-06-13
2018 Gen Nishida, Adrien Bousseau, Daniel G. Aliaga
Procedural Modeling of a Building from a Single Image
published pages: 415-429, ISSN: 0167-7055, DOI: 10.1111/cgf.13372
Computer Graphics Forum 37/2 2019-06-13
2017 Amélie Fondevilla, Adrien Bousseau, Damien Rohmer, Stefanie Hahmann, Marie-Paule Cani
Patterns from photograph: Reverse-engineering developable products
published pages: 4-13, ISSN: 0097-8493, DOI: 10.1016/j.cag.2017.05.017
Computers & Graphics 66 2019-06-13
2017 Favreau , Jean-Dominique; Lafarge , Florent; Bousseau , Adrien ,
Photo2ClipArt: Image Abstraction and Vectorization Using Layered Linear Gradients
published pages: , ISSN: 0730-0301, DOI: 10.1145/3130800.3130888
ACM Transactions on Graphics 6 2019-06-13

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "D3" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email ( and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "D3" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)

SiMS (2019)

Simulated Majorana states

Read More  

TORYD (2020)

TOpological many-body states with ultracold RYDberg atoms

Read More  

CELPRED (2020)

Circuit elements of the cortical circuit for predictive processing

Read More