Yannick Hold-Geoffroy
Yannick Hold
I am a senior research scientist and engineer at Adobe Research. My research sits at the intersection of computer vision, computer graphics, and machine learning, and focuses on learning and using priors from natural images. I'm interested in teaching machines to perceive and control geometry, materials, and lighting in service of creative tools. At Adobe, I worked on Stager's match image perspective and lighting technologies, and my research has been integrated into Photoshop's Neural Filters and Adobe Firefly.
I received my Ph.D. from the Computer Vision and Systems Laboratory of Laval University under the supervision of Jean-François Lalonde and Paulo Gotardo. My thesis received the 2018 CIPPRS Doctoral Dissertation Award.
I can be reached by email at holdgeof@ad*be.com.
Research
Snapshot polarimetric
diffuse-specular separationAkshat Dave, Yannick Hold-Geoffroy, Miloš Hašan, Kalyan Sunkavalli, Ashok Veeraraghavan
Optics Express, 2022
[PDF]
Guided Co-Modulated GAN for 360° Field of View
ExtrapolationMohammad Reza Karimi Dastjerdi, Yannick Hold-Geoffroy, Jonathan Eisenmann, Siavash Khodadadeh, J.-F. Lalonde
International Conference on 3D Vision (3DV), 2022
[Project Page]
[ArXiv]
Material Swapping for 3D Scenes using a
Learnt Material Similarity MeasureMaxine Perroni-Scharf, Kalyan Sunkavalli, Jonathan Eisenmann, Yannick Hold-Geoffroy
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Presented at the Women in Computer Vision Workshop
[Project page]
[PDF]
Presented at the Women in Computer Vision Workshop
PhotoScene: Photorealistic
Material and Lighting Transfer for Indoor ScenesYu-Ying Yeh, Zhengqin Li, Yannick Hold-Geoffroy, Rui Zhu, Zexiang Xu, Miloš Hašan, Kalyan Sunkavalli, Manmohan Chandraker
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[Project page]
[ArXiv]
[PDF]
[Code]
Temporally
Consistent Relighting for Portrait VideosSreenithy Chandran, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Zhixin Shu, Suren Jayasuriya
Workshop on Applications of Computational Imaging co-located with WACV, 2022
[PDF]
NeuTex: Neural Texture Mapping for Volumetric Neural
RenderingFanbo Xiang, Zexiang Xu, Miloš Hašan, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Hao Su
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[ArXiv]
[PDF]
[Video]
[Code]
Deep Reflectance Volumes: Relightable
Reconstructions from Multi-View Photometric ImagesSai Bi, Zexiang Xu, Kalyan Sunkavalli, Miloš Hašan, Yannick Hold-Geoffroy, David Kriegman, Ravi Ramamoorthi
European Conference on Computer Vision, 2020 (spotlight)
[PDF]
[Supplement]
[Video]
Deep Multi Depth Panoramas for View
SynthesisKai-En Lin, Zexiang Xu, Ben Mildenhall, Pratul P. Srinivasan, Yannick Hold-Geoffroy, Stephen DiVerdi, Qi Sun, Kalyan Sunkavalli, Ravi Ramamoorthi
European Conference on Computer Vision, 2020
Single View Metrology in the WildRui Zhu, Xingyi Yang, Yannick Hold-Geoffroy, Federico Perazzi, Jonathan Eisenmann, Kalyan Sunkavalli, Manmohan Chandraker
European Conference on Computer Vision, 2020
[PDF (preprint)]
[PDF]
[Slides]
[Video]
LandscapeAR: Large Scale Outdoor Augmented
Reality by Matching Photographs with Terrain Models Using Learned DescriptorsJan Brejcha, Michal Lukáč, Yannick Hold-Geoffroy, Oliver Wang, Martin Čadík,
European Conference on Computer Vision, 2020
RGB2AO: Ambient Occlusion
Generation from RGB ImagesNaoto Inoue, Daichi Ito, Yannick Hold-Geoffroy, Long Mai, Brian Price, Toshihiko Yamasaki
Computer Graphics Forum (proceedings of Eurographics), 2020
[PDF (preprint)]
[PDF]
[Supplement]
[BibTeX]
[Video]
AutoToon: Automatic Geometric Warping
for Face Cartoon GenerationJulia Gong, Yannick Hold-Geoffroy, Jingwan Lu
The IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
Single Day Outdoor Photometric StereoYannick Hold-Geoffroy, P. F. U. Gotardo, and J.-F. Lalonde
IEEE Transations on Pattern Analysis and Machine Intelligence (TPAMI), 2020
Deep Parametric Indoor Lighting
EstimationMarc-André Gardner, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Christian Gagné, J.-F. Lalonde
IEEE International Conference on Computer Vision (ICCV), 2019
Deep Sky Modeling for Single Image Outdoor
Lighting EstimationYannick Hold-Geoffroy, Akshaya Athwale, and Jean-François Lalonde
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Oral presentation!
All-Weather Deep Outdoor Lighting
EstimationJinsong Zhang, Kalyan Sunkavalli, Yannick Hold-Geoffroy, Sunil Hadap, J Eisenmann, and Jean-François Lalonde
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
A
Perceptual Measure for Deep Single Image Camera CalibrationYannick Hold-Geoffroy, Kalyan Sunkavalli, J Eisenmann, Matthew Fisher, Sunil Hadap, Emiliano Gambaretto, and Jean-François Lalonde
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Demo available on the project webpage.
Deep Outdoor
Illumination EstimationYannick Hold-Geoffroy, Kalyan Sunkavalli, Sunil Hadap, Emiliano Gambaretto, and Jean-François Lalonde
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Oral presentation!
Demo available on the project
webpage.
x-hour Outdoor
Photometric StereoYannick Hold-Geoffroy, Jinsong Zhang, Paulo F. U. Gotardo, and Jean-François Lalonde
International Conference on 3D Vision (3DV), 2015
Best paper award (runner up)!
Code and data available.
What Is a Good Day for
Outdoor Photometric Stereo?Yannick Hold-Geoffroy, Jinsong Zhang, Paulo F. U. Gotardo, and Jean-François Lalonde
IEEE International Conference on Computational Photography (ICCP), 2015
Code and data available.