Related papers: Difference-in-Differences: Bridging Normalization …

In image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances. Intermediates must remain faithful to the input, stand on their own as members of the set,…

Despite the demonstrated editing capacity in the latent space of a pretrained GAN model, inverting real-world images is stuck in a dilemma that the reconstruction cannot be faithful to the original input. The main reason for this is that…

Deep neural advancements have recently brought remarkable image synthesis performance to the field of image inpainting. The adaptation of generative adversarial networks (GAN) in particular has accelerated significant progress in…

Inpainting involves filling in missing pixels or areas in an image, a crucial technique employed in Mixed Reality environments for various applications, particularly in Diminished Reality (DR) where content is removed from a user's visual…

The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images. GAN based techniques such as Image-to-Image translations, DeepFakes, and other automated…

A fundamental challenge for machine learning models is generalizing to out-of-distribution (OOD) data, in part due to spurious correlations. To tackle this challenge, we first formalize the OOD generalization problem as constrained…

The impressive success of style-based GANs (StyleGANs) in high-fidelity image synthesis has motivated research to understand the semantic properties of their latent spaces. In this paper, we approach this problem through a geometric…

The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels extracted from images, engenders complex correlations.…

We consider the generic deep image enhancement problem where an input image is transformed into a perceptually better-looking image. Recent methods for image enhancement consider the problem by performing style transfer and image…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Video object segmentation is a fundamental step in many advanced vision applications. Most existing algorithms are based on handcrafted features such as HOG, super-pixel segmentation or texture-based techniques, while recently deep features…

We propose FineGAN, a novel unsupervised GAN framework, which disentangles the background, object shape, and object appearance to hierarchically generate images of fine-grained object categories. To disentangle the factors without…

A core challenge in Machine Learning is to learn to disentangle natural factors of variation in data (e.g. object shape vs. pose). A popular approach to disentanglement consists in learning to map each of these factors to distinct subspaces…

We present a deep learning framework based on a generative adversarial network (GAN) to perform super-resolution in coherent imaging systems. We demonstrate that this framework can enhance the resolution of both pixel size-limited and…

The large pose discrepancy between two face images is one of the fundamental challenges in automatic face recognition. Conventional approaches to pose-invariant face recognition either perform face frontalization on, or learn a…

Latent traversal is a popular approach to visualize the disentangled latent representations. Given a bunch of variations in a single unit of the latent representation, it is expected that there is a change in a single factor of variation of…

One of the important research topics in image generative models is to disentangle the spatial contents and styles for their separate control. Although StyleGAN can generate content feature vectors from random noises, the resulting spatial…

Image manipulation detection and localization have received considerable attention from the research community given the blooming of Generative Models (GMs). Detection methods that follow a passive approach may overfit to specific GMs,…

Biomedical image datasets can be imbalanced due to the rarity of targeted diseases. Generative Adversarial Networks play a key role in addressing this imbalance by enabling the generation of synthetic images to augment datasets. It is…

In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these…