• Computer Science
  • Published in ICCV 2019

HoloGAN: Unsupervised learning of 3D representations from natural images

@article{NguyenPhuoc2019HoloGANUL,
  title={HoloGAN: Unsupervised learning of 3D representations from natural images},
  author={Thu Nguyen-Phuoc and Chuan Li and Lucas Theis and Christian Richardt and Yongliang Yang},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.01326}
}
We propose a novel generative adversarial network (GAN) for the task of unsupervised learning of 3D representations from natural images. Most generative models rely on 2D kernels to generate images and make few assumptions about the 3D world. These models therefore tend to create blurry images or artefacts in tasks that require a strong 3D understanding, such as novel-view synthesis. HoloGAN instead learns a 3D representation of the world, and to render this representation in a realistic manner… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 18 CITATIONS

Self-supervised Learning of 3D Objects from Natural Images

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

SynSin: End-to-end View Synthesis from a Single Image

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Fine-grained Image-to-Image Transformation towards Visual Recognition

VIEW 1 EXCERPT
CITES BACKGROUND

3D Ken Burns effect from a single image

VIEW 2 EXCERPTS
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 70 REFERENCES

A Style-Based Generator Architecture for Generative Adversarial Networks

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Visual Object Networks: Image Generation with Disentangled 3D Representations

VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Neural scene representation and rendering

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Pix2Scene: Learning Implicit 3D Representations from Images

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

A large-scale car dataset for fine-grained categorization and verification

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL