Time-travel rephotography

@article{Luo2021TimetravelR,
  title={Time-travel rephotography},
  author={Xuan Luo and Xuaner Cecilia Zhang and Paul Yoo and Ricardo Martin-Brualla and Jason Lawrence and Steven M. Seitz},
  journal={ACM Transactions on Graphics (TOG)},
  year={2021},
  volume={40},
  pages={1 - 12}
}
Many historical people were only ever captured by old, faded, black and white photos, that are distorted due to the limitations of early cameras and the passage of time. This paper simulates traveling back in time with a modern camera to rephotograph famous subjects. Unlike conventional image restoration filters which apply independent operations like denoising, colorization, and superresolution, we leverage the StyleGAN2 framework to project old photos into the space of modern high-resolution… 

Figures and Tables from this paper

Panini-Net: GAN Prior Based Degradation-Aware Feature Interpolation for Face Restoration

A novel GAN Prior based degradation-aware feature interpolation network, dubbed Panini-Net, for FR tasks by explicitly learning the abstract representations to distinguish various degradations, achieves state-of-the-art performance for multi-degradation face restoration and face super-resolution.

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex

How to Guide Adaptive Depth Sampling?

It is shown that a neural network can learn to produce a highly faithful Importance Map, given an RGB image, and is validated through sim-ulations that this approach outperforms grid and random sampling patterns as well as recent state-of-the-art adaptive algorithms.

MyStyle: A Personalized Generative Prior

We introduce MyStyle, a personalized deep generative prior trained with a few shots of an individual. MyStyle allows to reconstruct, enhance and edit images of a specific person, such that the output

State‐of‐the‐Art in the Architecture, Methods and Applications of StyleGAN

This state‐of‐the‐art report covers the StyleGAN architecture, and the ways it has been employed since its conception, while also analyzing its severe limitations.

Synthesis and Reconstruction of Fingerprints using Generative Adversarial Networks

This work proposes a novel fingerprint synthesis and reconstruction framework based on the StyleGan2 architecture that significantly improved the realism of the generated fingerprints, both visually and in terms of their ability to spoof fingerprint-based verification systems.

‘I’m your automatic colour’ La colorazione automatica delle immagini in antropologia

Colour photographs now represent almost all the images produced with the new reality capture tools, mobile phones, which in 2020 ‘took’ 90% of all photos of that year. Black and white is relegated to

StyleAlign: Analysis and Applications of Aligned StyleGAN Models

This paper empirically an-alyze aligned models and provides answers to important questions regarding their nature, and shows that the child model’s latent spaces are semantically aligned with those of the parent, inheriting incredibly rich semantics, even for distant data domains such as human faces and churches.

Labels4Free: Unsupervised Segmentation using StyleGAN

This work proposes to augment the StyleGAN2 generator architecture with a segmentation branch and to split the generator into a foreground and background network, allowing it to generate soft segmentation masks for the foreground object in an unsupervised fashion.

References

SHOWING 1-10 OF 98 REFERENCES

Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation

We present a generic image-to-image translation framework, pixel2style2pixel (pSp). Our pSp framework is based on a novel encoder network that directly generates a series of style vectors which are

Instance-Aware Image Colorization

This paper proposes a method for achieving instance-aware colorization that leverages an off-the-shelf object detector to obtain cropped object images and uses an instance colorization network to extract object-level features and applies a fusion module to full object- level and image- level features to predict the final colors.

Feedback Network for Image Super-Resolution

An image super-resolution feedback network (SRFBN) is proposed to refine low-level representations with high-level information by using hidden states in a recurrent neural network (RNN) with constraints to achieve such feedback manner.

A Style-Based Generator Architecture for Generative Adversarial Networks

An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation.

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

jantic/deoldify: A deep learning based project for colorizing and restoring old images (and video!)

  • 2019

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

This work presents a novel super-resolution algorithm, PULSE (Photo Upsampling via Latent Space Exploration), which generates high-resolution, realistic images at resolutions previously unseen in the literature, and outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.

On the Variance of the Adaptive Learning Rate and Beyond

This work identifies a problem of the adaptive learning rate, suggests warmup works as a variance reduction technique, and proposes RAdam, a new variant of Adam, by introducing a term to rectify the variance of theadaptive learning rate.

A history of photography : from 1839 to the present

From a delivery boy to one of the most important industrialists in American history, George Eastman's career developed in a particularly American way. The founder of Kodak died in 1932, and left his

Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?

We propose an efficient algorithm to embed a given image into the latent space of StyleGAN. This embedding enables semantic image editing operations that can be applied to existing photographs.
...