Related papers: Positional Encoding as Spatial Inductive Bias in G…
While GAN is a powerful model for generating images, its inability to infer a latent space directly limits its use in applications requiring an encoder. Our paper presents a simple architectural setup that combines the generative…
Positional encoding is essential for supplementing transformer with positional information of tokens. Existing positional encoding methods demand predefined token/feature order, rendering them unsuitable for real-world data with…
Convolution is an equivariant operation, and image position does not affect its result. A recent study shows that the zero-padding employed in convolutional layers of CNNs provides position information to the CNNs. The study further claims…
Recent advances in deep generative models have shown promising potential in image inpanting, which refers to the task of predicting missing pixel values of an incomplete image using the known context. However, existing methods can be slow…
The inverse mapping of GANs'(Generative Adversarial Nets) generator has a great potential value.Hence, some works have been developed to construct the inverse function of generator by directly learning or adversarial learning.While the…
In the paper we construct a fully convolutional GAN model: LocoGAN, which latent space is given by noise-like images of possibly different resolutions. The learning is local, i.e. we process not the whole noise-like image, but the…
In this paper, we present InSeGAN, an unsupervised 3D generative adversarial network (GAN) for segmenting (nearly) identical instances of rigid objects in depth images. Using an analysis-by-synthesis approach, we design a novel GAN…
While generative adversarial networks (GANs) have revolutionized machine learning, a number of open questions remain to fully understand them and exploit their power. One of these questions is how to efficiently achieve proper diversity and…
In an unpaired setting, lacking sufficient content constraints for image-to-image translation (I2I) tasks, GAN-based approaches are usually prone to model collapse. Current solutions can be divided into two categories, reconstruction-based…
Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part…
Positional encodings are employed to capture the high frequency information of the encoded signals in implicit neural representation (INR). In this paper, we propose a novel positional encoding method which improves the reconstruction…
Generative models have made significant progress in the tasks of modeling complex data distributions such as natural images. The introduction of Generative Adversarial Networks (GANs) and auto-encoders lead to the possibility of training on…
Generative adversarial networks (GANs), e.g., StyleGAN2, play a vital role in various image generation and synthesis tasks, yet their notoriously high computational cost hinders their efficient deployment on edge devices. Directly applying…
In this paper, we introduce the spatial bias to learn global knowledge without self-attention in convolutional neural networks. Owing to the limited receptive field, conventional convolutional neural networks suffer from learning long-range…
Deep generative models like StyleGAN hold the promise of semantic image editing: modifying images by their content, rather than their pixel values. Unfortunately, working with arbitrary images requires inverting the StyleGAN generator,…
Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples ($x$) conditioned on both latent variables ($z$) and known auxiliary information ($c$). We propose the Bidirectional cGAN (BiCoGAN),…
Unconditional video generation is a challenging task that involves synthesizing high-quality videos that are both coherent and of extended duration. To address this challenge, researchers have used pretrained StyleGAN image generators for…
Vector quantization approaches (VQ-VAE, VQ-GAN) learn discrete neural representations of images, but these representations are inherently position-dependent: codes are spatially arranged and contextually entangled, requiring autoregressive…
The enduring inability of image generative models to recreate intricate geometric features, such as those present in human hands and fingers has been an ongoing problem in image generation for nearly a decade. While strides have been made…
We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. Unlike RNN and LSTM, which contain inductive bias by loading the input tokens sequentially, non-recurrent models are…