Aligning and Projecting Images to Class-conditional Generative Networks
We present a method for projecting an input image into the space of a class-conditional generative neural network. We propose a method that optimizes for transformation to counteract the model biases in generative neural networks. Specifically, we demonstrate that one can solve for image translation, scale, and global color transformation, during the projection optimization to address the object-center bias and color bias of a Generative Adversarial Network. This projection process poses a difficult optimization problem, and purely gradient-based optimizations fail to find good solutions. We describe a hybrid optimization strategy that finds good projections by estimating transformations and class parameters. We show the effectiveness of our method on real images and further demonstrate how the corresponding projections lead to better editability of these images.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkTranslationSimilar Papers 제목 키워드 기반
Transforming and Projecting Images into Class-conditional Generative Networks
We present a method for projecting an input image into the space of a class-conditional generative neural network. We propose a method that optimizes for transformation to counteract the model biases in generative neural…
Generative Adversarial NetworkTranslationClass-Continuous Conditional Generative Neural Radiance Field
The 3D-aware image synthesis focuses on conserving spatial consistency besides generating high-resolution images with fine details. Recently, Neural Radiance Field (NeRF) has been introduced for synthesizing novel views …
3D-Aware Image SynthesisImage GenerationImage-to-Image TranslationNeRFAlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
Recently, several methods based on generative adversarial network (GAN) have been proposed for the task of aligning cross-domain images or learning a joint distribution of cross-domain images. One of the methods is to us…
Generative Adversarial NetworkSphericGAN: Semi-Supervised Hyper-Spherical Generative Adversarial Networks for Fine-Grained Image Synthesis
Generative Adversarial Network (GAN)-based models have greatly facilitated image synthesis. However, the model performance may be degraded when applied to fine-grained data, due to limited training samples and subtle…
Generative Adversarial NetworkImage GenerationRebooting ACGAN: Auxiliary Classifier GANs with Stable Training
Conditional Generative Adversarial Networks (cGAN) generate realistic images by incorporating class information into GAN. While one of the most popular cGANs is an auxiliary classifier GAN with softmax cross-entropy loss…
Conditional Image GenerationDiversityGenerative Adversarial NetworkImage Generation