By Aaron Hertzmann, Adobe Research
This year, Adobe Research continued in its core mission of developing innovative new technologies, publishing 66 research papers at the top computer vision and computer graphics conferences:
- CVPR 2017: Adobe authors contributed to 26 papers
- SIGGRAPH 2017: Adobe authors contributed to 17 papers, plus 2 Transactions on Graphics (TOG) papers
- ICCV 2017: Adobe authors contributed to 17 papers
- SIGGRAPH Asia 2017: Adobe authors contributed to 4 papers
Nearly all of these papers came from university collaborations. Most were first-authored by university PhD students following successful summer internships working with Adobe researchers. (Find instructions on applying for a 2018 internship here.)
These are substantial numbers of papers for any university or lab. At SIGGRAPH 2017, 127 papers were published in total, meaning that Adobe researchers co-authored more than one-eighth of the papers at SIGGRAPH this year.
In addition, Adobe researchers received three Helmholtz test-of-time awards at ICCV 2017, recognizing significant long-term impact on the field of computer vision. Adding to these numbers, we also published eight papers at NIPS, the machine learning conference.
A few publications
Here is a sampling of some of these papers:
Deep Photo Style Transfer
Fujun Luan, Sylvain Paris, Eli Shechtman, Kavita Bala
CVPR 2017
[ Paper ] [ Project Page ]
Controlling Perceptual Factors in Neural Style Transfer
Leon Gatys, Alexander S. Ecker, Matthias Bethge, Aaron Hertzmann, Eli Shechtman.
CVPR 2017
[ Paper ]
Scribbler: Controlling Deep Image Synthesis with Sketch and Color
Patsorn Sangkloy, Jingwan Lu, Chen Fang, Fisher Yu, James Hays
CVPR 2017
[ Project page ] [ Adobe MAX Sneak ]
Deep Outdoor Illumination Estimation
Yannick Hold-Geoffroy, Kalyan Sunkavalli, Sunil Hadap, Emiliano Gambaretto, Jean-François Lalonde
CVPR 2017
[ Project page ]
Example-Based Synthesis of Stylized Facial Animations
Jakub Fišer, Ondřej Jamriška, David Simons, Eli Shechtman, Jingwan Lu, Paul Asente, Michal Lukáč, Daniel Sýkora
SIGGRAPH 2017
[ Paper ] [ Project page ] [ Adobe project page ] [Adobe MAX Sneak ]
VoCo: Text-based Insertion and Replacement in Audio Narration
Zeyu Jin, Gautham J. Mysore, Stephen DiVerdi, Jingwan Lu, Adam Finkelstein
SIGGRAPH 2017
[ Project page ] [ Adobe MAX Sneak ]
Playful Palette: An Interactive Parametric Color Mixer for Artists
Maria Shugrina, Jingwan Lu, Stephen DiVerdi
SIGGRAPH 2017
[ Adobe MAX Sneak ]
Functionality-aware Retargeting of Mechanisms to 3D Shapes
Ran Zhang, Thomas Auzinger, Duygu Ceylan, Wilmot Li, and Bernd Bickel
SIGGRAPH 2017
[ Paper ] [ Project Page ] [ News Story ]
Localizing Moments in Video with Natural Language
Lisa Anne Hendricks,, Oliver Wang, Eli Shechtman, Josef Sivic, Trevor Darrell, Bryan Russell
ICCV 2017
[ Project page ] [ Paper ]
BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography
Michael J. Wilber, Chen Fang, Hailin Jin, Aaron Hertzmann, John Collomosse, Serge Belongie
ICCV 2017
[ Project page ] [ Paper ]
Robust Video Super-Resolution With Learned Temporal Dynamics
Ding Liu, Zhaowen Wang, Yuchen Fan, Xianming Liu, Zhangyang Wang, Shiyu Chang, Thomas Huang
ICCV 2017
[ Paper ]
FoveaNet: Perspective-Aware Urban Scene Parsing
Xin Li, Zequn Jie, Wei Wang, Changsong Liu, Jimei Yang, Xiaohui Shen, Zhe Lin, Qiang Chen, Shuicheng Yan, Jiashi Feng
ICCV 2017
[ Paper ]
ComplementMe: Weakly-supervised Component Suggestion for 3D Modeling
Minhyuk Sung, Hao Su, Vladimir G. Kim, Siddhartha Chaudhuri, Leonidas Guibas
SIGGRAPH Asia 2017
[ Paper ]
Learning to Predict Indoor Illumination from a Single Image
Marc-Andre Gardner, Kalyan Sunkavalli, Ersin Yumer, Xiaohui Shen, Emiliano Gambaretto, Christian Gagné, Jean-François Lalonde
SIGGRAPH Asia 2017
[ Project page ]
Image: Automatic example-based face stylization with Puppetron presented at SIGGRAPH 2017, one of the many publications presented by Adobe Research scientists at visual computing conferences in 2017.
