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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Xingang Pan

Xingang Pan

GAN2X: Non-Lambertian Inverse Rendering of Image GANs



Xingang Pan , Ayush Tewari , Lingjie Liu , Christian Theobalt

* The video demo is available at the project page: https://people.mpi-inf.mpg.de/~xpan/GAN2X/ 
   Access Paper or Ask Questions

Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images



Ayush Tewari , Mallikarjun B R , Xingang Pan , Ohad Fried , Maneesh Agrawala , Christian Theobalt

Figure 1 for Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
Figure 2 for Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
Figure 3 for Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
Figure 4 for Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
* CVPR 2022 
   Access Paper or Ask Questions

CityNeRF: Building NeRF at City Scale



Yuanbo Xiangli , Linning Xu , Xingang Pan , Nanxuan Zhao , Anyi Rao , Christian Theobalt , Bo Dai , Dahua Lin

Figure 1 for CityNeRF: Building NeRF at City Scale
Figure 2 for CityNeRF: Building NeRF at City Scale
Figure 3 for CityNeRF: Building NeRF at City Scale
Figure 4 for CityNeRF: Building NeRF at City Scale
* Project page can be found in https://city-super.github.io/citynerf 
   Access Paper or Ask Questions

Generative Occupancy Fields for 3D Surface-Aware Image Synthesis



Xudong Xu , Xingang Pan , Dahua Lin , Bo Dai

Figure 1 for Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
Figure 2 for Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
Figure 3 for Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
Figure 4 for Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
* Accepted to NeurIPS2021. We propose Generative Occupancy Fields(GOF), a 3D-aware generative model which could synthesize realistic images with 3D consistency and simultaneously learn compact object surfaces 
   Access Paper or Ask Questions

A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis



Xingang Pan , Xudong Xu , Chen Change Loy , Christian Theobalt , Bo Dai

Figure 1 for A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
Figure 2 for A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
Figure 3 for A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
Figure 4 for A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
* Accepted to NeurIPS2021. We proposed ShadeGAN, which could perform shape-accurate 3D-aware image synthesis by modeling shading in generative implicit models 
   Access Paper or Ask Questions

Talk-to-Edit: Fine-Grained Facial Editing via Dialog



Yuming Jiang , Ziqi Huang , Xingang Pan , Chen Change Loy , Ziwei Liu

Figure 1 for Talk-to-Edit: Fine-Grained Facial Editing via Dialog
Figure 2 for Talk-to-Edit: Fine-Grained Facial Editing via Dialog
Figure 3 for Talk-to-Edit: Fine-Grained Facial Editing via Dialog
Figure 4 for Talk-to-Edit: Fine-Grained Facial Editing via Dialog
* To appear in ICCV2021. Project Page: https://www.mmlab-ntu.com/project/talkedit/, Code: https://github.com/yumingj/Talk-to-Edit 
   Access Paper or Ask Questions

Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs



Xingang Pan , Bo Dai , Ziwei Liu , Chen Change Loy , Ping Luo

Figure 1 for Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Figure 2 for Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Figure 3 for Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Figure 4 for Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs

   Access Paper or Ask Questions

Self-Supervised Scene De-occlusion



Xiaohang Zhan , Xingang Pan , Bo Dai , Ziwei Liu , Dahua Lin , Chen Change Loy

Figure 1 for Self-Supervised Scene De-occlusion
Figure 2 for Self-Supervised Scene De-occlusion
Figure 3 for Self-Supervised Scene De-occlusion
Figure 4 for Self-Supervised Scene De-occlusion
* Accepted to CVPR 2020 as oral. Project page: https://xiaohangzhan.github.io/projects/deocclusion/ 
   Access Paper or Ask Questions

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation



Xingang Pan , Xiaohang Zhan , Bo Dai , Dahua Lin , Chen Change Loy , Ping Luo

Figure 1 for Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Figure 2 for Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Figure 3 for Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Figure 4 for Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
* 1) Precise GAN-inversion by discriminator-guided generator finetuning. 2) A versatile way for high-quality image restoration and manipulation. Code: https://github.com/XingangPan/deep-generative-prior 
   Access Paper or Ask Questions
1
2
>>