Related papers: GANzzle: Reframing jigsaw puzzle solving as a retr…
Current generative frameworks use end-to-end learning and generate images by sampling from uniform noise distribution. However, these approaches ignore the most basic principle of image formation: images are product of: (a) Structure: the…
The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the…
Allowing effective inference of latent vectors while training GANs can greatly increase their applicability in various downstream tasks. Recent approaches, such as ALI and BiGAN frameworks, develop methods of inference of latent variables…
In this paper, we present a generative adversarial network framework that generates compressed images instead of synthesizing raw RGB images and compressing them separately. In the real world, most images and videos are stored and…
Image matting and image harmonization are two important tasks in image composition. Image matting, aiming to achieve foreground boundary details, and image harmonization, aiming to make the background compatible with the foreground, are…
Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specific heuristics…
Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with…
Popularized by the Differentiable Search Index, the emerging paradigm of generative retrieval re-frames the classic information retrieval problem into a sequence-to-sequence modeling task, forgoing external indices and encoding an entire…
Facial recognition using deep convolutional neural networks relies on the availability of large datasets of face images. Many examples of identities are needed, and for each identity, a large variety of images are needed in order for the…
With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable inputs. This paper focuses on a recent emerged task,…
Converting text descriptions into images using Generative Adversarial Networks has become a popular research area. Visually appealing images have been generated successfully in recent years. Inspired by these studies, we investigated the…
This paper investigates a general framework to discover categories of unlabeled scene images according to their appearances (i.e., textures and structures). We jointly solve the two coupled tasks in an unsupervised manner: (i) classifying…
This paper proposes a novel "auto-agglomerative" 3D fracture assembly method, PuzzleFusion++, resembling how humans solve challenging spatial puzzles. Starting from individual fragments, the approach 1) aligns and merges fragments into…
Computed medical imaging systems require a computational reconstruction procedure for image formation. In order to recover a useful estimate of the object to-be-imaged when the recorded measurements are incomplete, prior knowledge about the…
Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and replaying them during the…
Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently…
Generative networks are fundamentally different in their aim and methods compared to CNNs for classification, segmentation, or object detection. They have initially not been meant to be an image analysis tool, but to produce naturally…
We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…
Skill mastery is a priority for success in all fields. We present a parallel between the development of skill mastery and the process of solving jigsaw puzzles. We show that iterative random sampling solves jigsaw puzzles in two phases: a…
The aim of this work is learning to reshape the object in an input image to an arbitrary new shape, by just simply providing a single reference image with an object instance in the desired shape. We propose a new Generative Adversarial…