NeRF GAN

NeRF GANs combine the strengths of Neural Radiance Fields (NeRFs) for realistic 3D scene representation with Generative Adversarial Networks (GANs) for efficient generation and manipulation of images. Current research focuses on improving the speed and quality of 3D scene generation from limited data, including developing novel architectures like latent diffusion models and hypernetworks to enhance efficiency and control over lighting and geometry. This active research area is significant for its potential to revolutionize applications such as virtual and augmented reality, 3D modeling, and image editing by enabling high-fidelity, 3D-consistent image synthesis and manipulation.

Papers

June 18, 2024

Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models
Paul Henderson, Melonie de Almeida, Daniela Ivanova, Titas Anciukevičius
Latent Diffusion Model Multi View Diffusion Efficient Generative NeRF GAN

April 12, 2024

GPN: Generative Point-based NeRF
Haipeng Wang
Point Cloud Generative Question Point Cloud Completion Incomplete Point Cloud NeRF GAN

January 5, 2024

FED-NeRF: Achieve High 3D Consistency and Temporal Coherence for Face Video Editing on Dynamic NeRF
Hao Zhang, Yu-Wing Tai, Chi-Keung Tang
NeRF SLAM Face Editing 3D Consistency Temporal Coherence Dynamic NeRF NeRF GAN View Consistent Editing Face Video Editing

April 25, 2023

LumiGAN: Unconditional Generation of Relightable 3D Human Faces
Boyang Deng, Yifan Wang, Gordon Wetzstein
Generative Adversarial Network NeRF GAN Unconditional Generation 3D Human Face

March 23, 2023

TriPlaneNet: An Encoder for EG3D Inversion
Ananta R. Bhattarai, Matthias Nießner, Artem Sevastopolsky
Generative Modeling 3D GAN Inversion Seismic Inversion NeRF GAN

March 22, 2023

NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Mohamad Shahbazi, Evangelos Ntavelis, Alessio Tonioni, Edo Collins, Danda Pani Paudel, Martin Danelljan, Luc Van Gool
Generative Adversarial Network Direct Convolution 3D Generation Generative Neural Network NeRF GAN

January 27, 2023

HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
Adam Kania, Artur Kasymov, Maciej Zięba, Przemysław Spurek
Generative Model Neural Radiance Field GAN Architecture Hypernetwork Approach NeRF GAN Hyper Convolution

December 19, 2022

Correspondence Distillation from NeRF-based GAN
Yushi Lan, Chen Change Loy, Bo Dai
Neural Radiance Field GAN Model Dense Correspondence NeRF GAN Surface Correspondence

November 30, 2022

NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-shot Real Image Animation
Yu Yin, Kamran Ghasedi, HsiangTao Wu, Jiaolong Yang, Xin Tong, Yun Fu
GAN Inversion Real Image Animation NeRF GAN

July 21, 2022

Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
Jeong-gi Kwak, Yuanming Li, Dongsik Yoon, Donghyeon Kim, David Han, Hanseok Ko
GAN Model 2 Dimensional StyleGAN Latent 3D Perception Portrait Generation Portrait Synthesis NeRF GAN