Sketch2Normal: Deep networks for normal map generation

Wanchao Su; Xin Yang; Hongbo Fu

doi:10.1145/3145690.3145744

Sketch2Normal: Deep networks for normal map generation

Wanchao Su, Xin Yang, Hongbo Fu

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

2 Citations (Scopus)

Abstract

Normal maps are of great importance for many 2D graphics applications such as surface editing, re-lighting, texture mapping and 2D shading etc. Automatically inferring normal map is highly desirable for graphics designers. Many researchers have investigated the inference of normal map from intuitive and flexiable line drawing based on traditional geometric methods while our proposed deep networks-based method shows more robustness and provides more plausible results.

Original language	English
Title of host publication	SIGGRAPH Asia 2017 Posters, SA 2017
Editors	Diego Gutierrez, Hui Huang
Place of Publication	New York NY USA
Publisher	Association for Computing Machinery (ACM)
Number of pages	2
ISBN (Electronic)	9781450354059
DOIs	https://doi.org/10.1145/3145690.3145744
Publication status	Published - Nov 2017
Externally published	Yes
Event	ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia 2017 - Bangkok, Thailand Duration: 27 Nov 2017 → 30 Nov 2017 Conference number: 10th https://sa2017.siggraph.org/

Conference

Conference	ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia 2017
Abbreviated title	SIGGRAPH Asia 2017
Country/Territory	Thailand
City	Bangkok
Period	27/11/17 → 30/11/17
Internet address	https://sa2017.siggraph.org/

Keywords

Generative Adversarial Network
Normal Map
Sketch

Access to Document

10.1145/3145690.3145744

Cite this

@inproceedings{dbcdff5c582b48b1b7c488baafef4140,

title = "Sketch2Normal: Deep networks for normal map generation",

abstract = "Normal maps are of great importance for many 2D graphics applications such as surface editing, re-lighting, texture mapping and 2D shading etc. Automatically inferring normal map is highly desirable for graphics designers. Many researchers have investigated the inference of normal map from intuitive and flexiable line drawing based on traditional geometric methods while our proposed deep networks-based method shows more robustness and provides more plausible results.",

keywords = "Generative Adversarial Network, Normal Map, Sketch",

author = "Wanchao Su and Xin Yang and Hongbo Fu",

year = "2017",

month = nov,

doi = "10.1145/3145690.3145744",

language = "English",

editor = "Diego Gutierrez and Hui Huang",

booktitle = "SIGGRAPH Asia 2017 Posters, SA 2017",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

note = "ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia 2017, SIGGRAPH Asia 2017 ; Conference date: 27-11-2017 Through 30-11-2017",

url = "https://sa2017.siggraph.org/",

}

Su, W, Yang, X & Fu, H 2017, Sketch2Normal: Deep networks for normal map generation. in D Gutierrez & H Huang (eds), SIGGRAPH Asia 2017 Posters, SA 2017., 34, Association for Computing Machinery (ACM), New York NY USA, ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia 2017, Bangkok, Thailand, 27/11/17. https://doi.org/10.1145/3145690.3145744

TY - GEN

T1 - Sketch2Normal

T2 - ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia 2017

AU - Su, Wanchao

AU - Yang, Xin

AU - Fu, Hongbo

N1 - Conference code: 10th

PY - 2017/11

Y1 - 2017/11

N2 - Normal maps are of great importance for many 2D graphics applications such as surface editing, re-lighting, texture mapping and 2D shading etc. Automatically inferring normal map is highly desirable for graphics designers. Many researchers have investigated the inference of normal map from intuitive and flexiable line drawing based on traditional geometric methods while our proposed deep networks-based method shows more robustness and provides more plausible results.

AB - Normal maps are of great importance for many 2D graphics applications such as surface editing, re-lighting, texture mapping and 2D shading etc. Automatically inferring normal map is highly desirable for graphics designers. Many researchers have investigated the inference of normal map from intuitive and flexiable line drawing based on traditional geometric methods while our proposed deep networks-based method shows more robustness and provides more plausible results.

KW - Generative Adversarial Network

KW - Normal Map

KW - Sketch

UR - https://www.scopus.com/pages/publications/85041368394

U2 - 10.1145/3145690.3145744

DO - 10.1145/3145690.3145744

M3 - Conference Paper

AN - SCOPUS:85041368394

BT - SIGGRAPH Asia 2017 Posters, SA 2017

A2 - Gutierrez, Diego

A2 - Huang, Hui

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

Y2 - 27 November 2017 through 30 November 2017

ER -

Sketch2Normal: Deep networks for normal map generation

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this