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

School of Creative Media

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › 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	Proceedings of SA ’17 SIGGRAPH Asia 2017 Posters
Publisher	Association for Computing Machinery
ISBN (Print)	978-1-4503-5405-9
DOIs	https://doi.org/10.1145/3145690.3145744
Publication status	Published - Nov 2017
Event	SIGGRAPH Asia 2017 (SA '17) - Bangkok, Thailand Duration: 27 Nov 2017 → 30 Nov 2017

Conference

Conference	SIGGRAPH Asia 2017 (SA '17)
Place	Thailand
City	Bangkok
Period	27/11/17 → 30/11/17

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Research Keywords

Generative Adversarial Network
Normal Map
Sketch

Access Output

10.1145/3145690.3145744

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{585a777dc73c4ade8bca0583e3a908cf,

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",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).; SIGGRAPH Asia 2017 (SA '17) ; Conference date: 27-11-2017 Through 30-11-2017",

year = "2017",

month = nov,

doi = "10.1145/3145690.3145744",

language = "English",

isbn = "978-1-4503-5405-9 ",

booktitle = "Proceedings of SA {\textquoteright}17 SIGGRAPH Asia 2017 Posters",

publisher = "Association for Computing Machinery",

address = "United States",

}

TY - GEN

T1 - Sketch2Normal

T2 - SIGGRAPH Asia 2017 (SA '17)

AU - Su, Wanchao

AU - Yang, Xin

AU - Fu, Hongbo

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

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

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85041368394&origin=recordpage

U2 - 10.1145/3145690.3145744

DO - 10.1145/3145690.3145744

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-1-4503-5405-9

BT - Proceedings of SA ’17 SIGGRAPH Asia 2017 Posters

PB - Association for Computing Machinery

Y2 - 27 November 2017 through 30 November 2017

ER -

Sketch2Normal: Deep Networks for Normal Map Generation

Abstract

Conference

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this