Alias-Free Generative Adversarial Networks
- URL: http://arxiv.org/abs/2106.12423v1
- Date: Wed, 23 Jun 2021 14:20:01 GMT
- Title: Alias-Free Generative Adversarial Networks
- Authors: Tero Karras, Miika Aittala, Samuli Laine, Erik H\"ark\"onen, Janne
Hellsten, Jaakko Lehtinen, Timo Aila
- Abstract summary: generative adversarial networks depend on absolute pixel coordinates in an unhealthy manner.
We trace the root cause to careless signal processing that causes aliasing in the generator network.
Our results pave the way for generative models better suited for video and animation.
- Score: 48.09216521763342
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We observe that despite their hierarchical convolutional nature, the
synthesis process of typical generative adversarial networks depends on
absolute pixel coordinates in an unhealthy manner. This manifests itself as,
e.g., detail appearing to be glued to image coordinates instead of the surfaces
of depicted objects. We trace the root cause to careless signal processing that
causes aliasing in the generator network. Interpreting all signals in the
network as continuous, we derive generally applicable, small architectural
changes that guarantee that unwanted information cannot leak into the
hierarchical synthesis process. The resulting networks match the FID of
StyleGAN2 but differ dramatically in their internal representations, and they
are fully equivariant to translation and rotation even at subpixel scales. Our
results pave the way for generative models better suited for video and
animation.
Related papers
- SyntStereo2Real: Edge-Aware GAN for Remote Sensing Image-to-Image Translation while Maintaining Stereo Constraint [1.8749305679160366]
Current methods involve combining two networks, an unpaired image-to-image translation network and a stereo-matching network.
We propose an edge-aware GAN-based network that effectively tackles both tasks simultaneously.
We demonstrate that our model produces qualitatively and quantitatively superior results than existing models, and its applicability extends to diverse domains.
arXiv Detail & Related papers (2024-04-14T14:58:52Z) - Pixel-Inconsistency Modeling for Image Manipulation Localization [63.54342601757723]
Digital image forensics plays a crucial role in image authentication and manipulation localization.
This paper presents a generalized and robust manipulation localization model through the analysis of pixel inconsistency artifacts.
Experiments show that our method successfully extracts inherent pixel-inconsistency forgery fingerprints.
arXiv Detail & Related papers (2023-09-30T02:54:51Z) - Dual Pyramid Generative Adversarial Networks for Semantic Image
Synthesis [94.76988562653845]
The goal of semantic image synthesis is to generate photo-realistic images from semantic label maps.
Current state-of-the-art approaches, however, still struggle to generate realistic objects in images at various scales.
We propose a Dual Pyramid Generative Adversarial Network (DP-GAN) that learns the conditioning of spatially-adaptive normalization blocks at all scales jointly.
arXiv Detail & Related papers (2022-10-08T18:45:44Z) - Revisiting Domain Generalized Stereo Matching Networks from a Feature
Consistency Perspective [65.37571681370096]
We propose a simple pixel-wise contrastive learning across the viewpoints.
A stereo selective whitening loss is introduced to better preserve the stereo feature consistency across domains.
Our method achieves superior performance over several state-of-the-art networks.
arXiv Detail & Related papers (2022-03-21T11:21:41Z) - Realistic Full-Body Anonymization with Surface-Guided GANs [7.37907896341367]
We propose a new anonymization method that generates realistic humans for in-the-wild images.
A key part of our design is to guide adversarial nets by dense pixel-to-surface correspondences between an image and a canonical 3D surface.
We demonstrate that surface guidance significantly improves image quality and diversity of samples, yielding a highly practical generator.
arXiv Detail & Related papers (2022-01-06T18:57:59Z) - How Convolutional Neural Networks Deal with Aliasing [0.0]
We show that an image classifier CNN while, in principle, capable of implementing anti-aliasing filters, does not prevent aliasing from taking place in the intermediate layers.
In the first, we assess the CNNs capability of distinguishing oscillations at the input, showing that the redundancies in the intermediate channels play an important role in succeeding at the task.
In the second, we show that an image classifier CNN while, in principle, capable of implementing anti-aliasing filters, does not prevent aliasing from taking place in the intermediate layers.
arXiv Detail & Related papers (2021-02-15T18:52:47Z) - Disentangled Image Generation Through Structured Noise Injection [48.956122902434444]
We show that disentanglement in the first layer of the generator network leads to disentanglement in the generated image.
We achieve spatial disentanglement, scale-space disentanglement, and disentanglement of the foreground object from the background style.
This empirically leads to better disentanglement scores than state-of-the-art methods on the FFHQ dataset.
arXiv Detail & Related papers (2020-04-26T15:15:19Z) - A U-Net Based Discriminator for Generative Adversarial Networks [86.67102929147592]
We propose an alternative U-Net based discriminator architecture for generative adversarial networks (GANs)
The proposed architecture allows to provide detailed per-pixel feedback to the generator while maintaining the global coherence of synthesized images.
The novel discriminator improves over the state of the art in terms of the standard distribution and image quality metrics.
arXiv Detail & Related papers (2020-02-28T11:16:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.