Related papers: 4KLSDB: A Large-Scale Dataset for 4K Image Restora…

Due to the data-driven nature of current face identity (FaceID) customization methods, all state-of-the-art models rely on large-scale datasets containing millions of high-quality text-image pairs for training. However, none of these…

Currently, when reliable training datasets are available, deep learning methods dominate the proposed solutions for image super-resolution. However, for remote sensing benchmarks, it is very expensive to obtain high spatial resolution…

Multimodal Large Language Models (MLLMs) have demonstrated impressive 2D image/video understanding capabilities. However, there are no publicly standardized benchmarks to assess the abilities of MLLMs in understanding the 4D objects (3D…

Transparent objects such as windows and bottles made by glass widely exist in the real world. Segmenting transparent objects is challenging because these objects have diverse appearance inherited from the image background, making them had…

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…

Reliable depth estimation under real optical conditions remains a core challenge for camera vision in systems such as autonomous robotics and augmented reality. Despite recent progress in depth estimation and depth-of-field rendering,…

We develop ImageNet-Think, a multimodal reasoning dataset designed to aid the development of Vision Language Models (VLMs) with explicit reasoning capabilities. Our dataset is built on 250,000 images from ImageNet21k dataset, providing…

Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become…

Collecting amounts of distorted/clean image pairs in the real world is non-trivial, which seriously limits the practical applications of these supervised learning-based methods on real-world image super-resolution (RealSR). Previous works…

Large Vision-Language Models (LVLMs) have recently garnered significant attention, with many efforts aimed at harnessing their general knowledge to enhance the interpretability and robustness of autonomous driving models. However, LVLMs…

The automated generation of design RTL based on large language model (LLM) and natural language instructions has demonstrated great potential in agile circuit design. However, the lack of datasets and benchmarks in the public domain…

Ultra-high-resolution (UHR) text-to-image (T2I) generation has seen notable progress. However, two key challenges remain : 1) the absence of a large-scale high-quality UHR T2I dataset, and (2) the neglect of tailored training strategies for…

The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements for high-quality…

The main challenge in applying state-of-the-art deep learning methods to predict image quality in-the-wild is the relatively small size of existing quality scored datasets. The reason for the lack of larger datasets is the massive resources…

Dataset distillation aims to compress large datasets into compact yet highly informative subsets that preserve the training behavior of the original data. While this concept has gained traction in classification, its potential for image…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…

Numerous HR applications are centered around resumes and job descriptions. While they can benefit from advancements in NLP, particularly large language models, their real-world adoption faces challenges due to absence of comprehensive…

Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details.…

As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic…