Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation


Sep 21, 2022
Yu-Ying Yeh, Koki Nagano, Sameh Khamis, Jan Kautz, Ming-Yu Liu, Ting-Chun Wang

* ACM Trans. Graph. 41, 6, Article 231 (December 2022), 21 pages 
* To appear in ACM Transactions on Graphics (SIGGRAPH Asia 2022). 21 pages, 25 figures, 7 tables. Project page: https://deepimagination.cc/Lumos/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis


May 14, 2022
Jonathan Tremblay, Moustafa Meshry, Alex Evans, Jan Kautz, Alexander Keller, Sameh Khamis, Charles Loop, Nathan Morrical, Koki Nagano, Towaki Takikawa, Stan Birchfield

* Project page at http://www.cs.umd.edu/~mmeshry/projects/rtmv 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars


Mar 29, 2022
Amit Raj, Umar Iqbal, Koki Nagano, Sameh Khamis, Pavlo Molchanov, James Hays, Jan Kautz

* Project page at https://dracon-avatars.github.io/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Efficient Geometry-aware 3D Generative Adversarial Networks


Dec 15, 2021
Eric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano, Boxiao Pan, Shalini De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, Gordon Wetzstein

* Project page: https://matthew-a-chan.github.io/EG3D 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Frame Averaging for Equivariant Shape Space Learning


Dec 03, 2021
Matan Atzmon, Koki Nagano, Sanja Fidler, Sameh Khamis, Yaron Lipman


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Hierarchical Neural Implicit Pose Network for Animation and Motion Retargeting


Dec 02, 2021
Sourav Biswas, Kangxue Yin, Maria Shugrina, Sanja Fidler, Sameh Khamis


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Fields as Learnable Kernels for 3D Reconstruction


Nov 26, 2021
Francis Williams, Zan Gojcic, Sameh Khamis, Denis Zorin, Joan Bruna, Sanja Fidler, Or Litany


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer


Oct 30, 2021
Wenzheng Chen, Joey Litalien, Jun Gao, Zian Wang, Clement Fuji Tsang, Sameh Khamis, Or Litany, Sanja Fidler


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations


Aug 30, 2021
Kangxue Yin, Jun Gao, Maria Shugrina, Sameh Khamis, Sanja Fidler

* Accepted to ICCV 2021. Supplementary material can be found on the project page: https://nv-tlabs.github.io/3DStyleNet/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation


Feb 10, 2020
Hossam Isack, Christian Haene, Cem Keskin, Sofien Bouaziz, Yuri Boykov, Shahram Izadi, Sameh Khamis


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>