3D-Aware Image Synthesis
23 papers with code • 3 benchmarks • 4 datasets
Benchmarks
These leaderboards are used to track progress in 3D-Aware Image Synthesis
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
FFHQ
CelebAMask-HQ
SynthRAD2023
3D-Point Cloud dataset of various geometrical terrains
Most implemented papers
pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
marcoamonteiro/pi-GAN
•
•
CVPR 2021
We have witnessed rapid progress on 3D-aware image synthesis, leveraging recent advances in generative visual models and neural rendering.
Pix2NeRF: Unsupervised Conditional $π$-GAN for Single Image to Neural Radiance Fields Translation
We propose a pipeline to generate Neural Radiance Fields~(NeRF) of an object or a scene of a specific class, conditioned on a single input image.
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
autonomousvision/graf
•
•
NeurIPS 2020
In contrast to voxel-based representations, radiance fields are not confined to a coarse discretization of the 3D space, yet allow for disentangling camera and scene properties while degrading gracefully in the presence of reconstruction ambiguity.
XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors
cpeng93/XraySyn
•
•
A radiograph visualizes the internal anatomy of a patient through the use of X-ray, which projects 3D information onto a 2D plane.
CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis
The style-based GAN (StyleGAN) architecture achieved state-of-the-art results for generating high-quality images, but it lacks explicit and precise control over camera poses.
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
xingangpan/shadegan
•
•
NeurIPS 2021
Motivated by the observation that a 3D object should look realistic from multiple viewpoints, these methods introduce a multi-view constraint as regularization to learn valid 3D radiance fields from 2D images.
Generative Occupancy Fields for 3D Surface-Aware Image Synthesis
sheldontsui/gof_neurips2021
•
•
NeurIPS 2021
In this paper, we propose Generative Occupancy Fields (GOF), a novel model based on generative radiance fields that can learn compact object surfaces without impeding its training convergence.
FENeRF: Face Editing in Neural Radiance Fields
MrTornado24/FENeRF
•
•
CVPR 2022
2D GANs can generate high fidelity portraits but with low view consistency.
3D-Aware Semantic-Guided Generative Model for Human Synthesis
However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications.
3D-aware Image Synthesis via Learning Structural and Textural Representations
genforce/volumegan
•
•
CVPR 2022
The feature field is further accumulated into a 2D feature map as the textural representation, followed by a neural renderer for appearance synthesis.
