Related papers: PixelArena: A benchmark for Pixel-Precision Visual…
A reliable method of quantifying the perceptual realness of AI-generated images and identifying visually inconsistent regions is crucial for practical use of AI-generated images and for improving photorealism of generative AI via realness…
Large Multimodal Models (LMMs) exhibit major shortfalls when interpreting images and, by some measures, have poorer spatial cognition than small children or animals. Despite this, they attain high scores on many popular visual benchmarks,…
Generative models have made it possible to synthesize highly realistic images, potentially providing an abundant data source for training machine learning models. Despite the advantages of these synthesizable data sources, the…
In this work, we present a simple yet effective framework to address the domain translation problem between different sensor modalities with unique data formats. By relying only on the semantics of the scene, our modular generative…
Deep generative models are rapidly gaining traction in medical imaging. Nonetheless, most generative architectures struggle to capture the underlying probability distributions of volumetric data, exhibit convergence problems, and offer no…
Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive ability to creatively generate personalized content across various contexts. However, current evaluations either are…
We introduce CurveBench, a benchmark for hierarchical topological reasoning from visual input. CurveBench consists of \textbf{756 images} of pairwise non-intersecting Jordan curves across easy, polygonal, topographic-inspired, maze-like,…
Large Multimodal Models (LMMs) are typically trained on vast corpora of image-text data but are often limited in linguistic coverage, leading to biased and unfair outputs across languages. While prior work has explored multimodal…
We present a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs). Conditional GANs have enabled a variety of applications, but the…
Recent years have seen rapid advances in AI-driven image generation. Early diffusion models emphasized perceptual quality, while newer multimodal models like GPT-4o-image integrate high-level reasoning, improving semantic understanding and…
Semantic communication (SemCom) has emerged as a promising technique for the next-generation communication systems, in which the generation at the receiver side is allowed with semantic features' recovery. However, the majority of existing…
With the rapid proliferation of image generative models, the authenticity of digital images has become a significant concern. While existing studies have proposed various methods for detecting AI-generated content, current benchmarks are…
Visual Question Answering (VQA) often requires coupling fine-grained perception with factual knowledge beyond the input image. Prior multimodal Retrieval-Augmented Generation (MM-RAG) systems improve factual grounding but lack an internal…
Recent Multimodal Large Language Models (MLLMs) demonstrate strong high-level visual reasoning on tasks such as visual question answering and image captioning. Yet existing benchmarks largely overlook their ability to capture fine-grained…
There is a growing interest in using generative adversarial networks (GANs) to produce image content that is indistinguishable from real images as judged by a typical person. A number of GAN variants for this purpose have been proposed,…
As LLMs advance their reasoning capabilities about the physical world, the absence of rigorous benchmarks for evaluating their ability to generate scientifically valid physical models has become a critical gap. Computational mechanics,…
Text rendering has recently emerged as one of the most challenging frontiers in visual generation, drawing significant attention from large-scale diffusion and multimodal models. However, text editing within images remains largely…
The powerful reasoning of modern Vision Language Models open a new frontier for advanced personalization study. However, progress in this area is critically hampered by the lack of suitable benchmarks. To address this gap, we introduce…
Understanding humor is a core aspect of social intelligence, yet it remains a significant challenge for Large Multimodal Models (LMMs). We introduce PixelHumor, a benchmark dataset of 2,800 annotated multi-panel comics designed to evaluate…
Semantic Segmentation is a significant research field in Computer Vision. Despite being a widely studied subject area, many visualization tools do not exist that capture segmentation quality and dataset statistics such as a class imbalance…