Related papers: OverLayBench: A Benchmark for Layout-to-Image Gene…
Recent advancements in Document Layout Analysis through Large Language Models and Multimodal Models have significantly improved layout detection. However, despite these improvements, challenges remain in addressing critical structural…
Diffusion models (DMs) have achieved significant success in generating imaginative images given textual descriptions. However, they are likely to fall short when it comes to real-life scenarios with intricate details. The low-quality,…
In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013]. We start with a scheme inspired by Auto-Context, but that is suitable in situations where the…
Synthetic dataset generation in Computer Vision, particularly for industrial applications, is still underexplored. Industrial defect segmentation, for instance, requires highly accurate labels, yet acquiring such data is costly and…
A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we…
Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, struggle with sequential editing: especially with maintaining…
Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve…
Text-to-image (T2I) models have garnered significant attention for generating high-quality images aligned with text prompts. However, rapid T2I model advancements reveal limitations in early benchmarks, lacking comprehensive evaluations,…
Occlusion perception, a critical foundation for human-level spatial understanding, embodies the challenge of integrating visual recognition and reasoning. Though multimodal large language models (MLLMs) have demonstrated remarkable…
Cinematography is a cornerstone of film production and appreciation, shaping mood, emotion, and narrative through visual elements such as camera movement, shot composition, and lighting. Despite recent progress in multimodal large language…
Edge-preserving image smoothing is an important step for many low-level vision problems. Though many algorithms have been proposed, there are several difficulties hindering its further development. First, most existing algorithms cannot…
Despite extensive research spanning several decades, class imbalance is still considered a profound difficulty for both machine learning and deep learning models. While data oversampling is the foremost technique to address this issue,…
Recent methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Notably, these methods are able to produce high-quality 3D scenes without training on 3D data. Due to the open-ended nature of the task, most…
While text-to-image generation has been extensively studied, generating images from scene graphs remains relatively underexplored, primarily due to challenges in accurately modeling spatial relationships and object interactions. To fill…
The interest of the deep learning community in image synthesis has grown massively in recent years. Nowadays, deep generative methods, and especially Generative Adversarial Networks (GANs), are leading to state-of-the-art performance,…
The burgeoning field of generative artificial intelligence has fundamentally reshaped our approach to content creation, with Large Vision-Language Models (LVLMs) standing at its forefront. While current LVLMs have demonstrated impressive…
Autoscaling has become a baseline expectation for cloud-native big data processing, and the design space has expanded beyond rule-based heuristics to include learned controllers and, most recently, large language model (LLM) agents. Yet…
Recent advancements in diffusion models have enabled a wide range of works exploiting their ability to generate high-volume, high-quality data for use in various downstream tasks. One subclass of such models, dubbed Layout-to-Image…
Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new challenges for verifying visual evidence. A concrete emerging risk is AI-generated refund…
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the…