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

Large-scale dataset distillation requires storing auxiliary soft labels that can be 30-40x larger on ImageNet-1K and 200x larger on ImageNet-21K than the condensed images, undermining the goal of dataset compression. We identify two…

We present TableBank, a new image-based table detection and recognition dataset built with novel weak supervision from Word and Latex documents on the internet. Existing research for image-based table detection and recognition usually…

High-quality human reconstruction and photo-realistic rendering of a dynamic scene is a long-standing problem in computer vision and graphics. Despite considerable efforts invested in developing various capture systems and reconstruction…

Human head detection, keypoint estimation, and 3D head model fitting are essential tasks with many applications. However, traditional real-world datasets often suffer from bias, privacy, and ethical concerns, and they have been recorded in…

High-resolution image (HRI) understanding aims to process images with a large number of pixels, such as pathological images and agricultural aerial images, both of which can exceed 1 million pixels. Vision Large Language Models (VLMs) can…

While recent advancements in vision-language models have had a transformative impact on multi-modal comprehension, the extent to which these models possess the ability to comprehend generated images remains uncertain. Synthetic images, in…

We study on image super-resolution (SR), which aims to recover realistic textures from a low-resolution (LR) image. Recent progress has been made by taking high-resolution images as references (Ref), so that relevant textures can be…

Scientific figure interpretation is a crucial capability for AI-driven scientific assistants built on advanced Large Vision Language Models. However, current datasets and benchmarks primarily focus on simple charts or other relatively…

Vehicles, pedestrians, and riders are the most important and interesting objects for the perception modules of self-driving vehicles and video surveillance. However, the state-of-the-art performance of detecting such important objects (esp.…

While image retrieval and instance recognition techniques are progressing rapidly, there is a need for challenging datasets to accurately measure their performance -- while posing novel challenges that are relevant for practical…

The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed…

Restoring low-resolution text images presents a significant challenge, as it requires maintaining both the fidelity and stylistic realism of the text in restored images. Existing text image restoration methods often fall short in hard…

To train a deblurring network, an appropriate dataset with paired blurry and sharp images is essential. Existing datasets collect blurry images either synthetically by aggregating consecutive sharp frames or using sophisticated camera…

While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compared with other computer vision tasks, it is rather difficult…

Depth maps obtained by commercial depth sensors are always in low-resolution, making it difficult to be used in various computer vision tasks. Thus, depth map super-resolution (SR) is a practical and valuable task, which upscales the depth…

Increasing popularity of high-dynamic-range (HDR) image and video content brings the need for metrics that could predict the severity of image impairments as seen on displays of different brightness levels and dynamic range. Such metrics…

Current state-of-the-art image generation models such as Latent Diffusion Models (LDMs) have demonstrated the capacity to produce visually striking food-related images. However, these generated images often exhibit an artistic or surreal…

High-quality labeled datasets play a crucial role in fueling the development of machine learning (ML), and in particular the development of deep learning (DL). However, since the emergence of the ImageNet dataset and the AlexNet model in…

This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution. Recently, some methods on dynamic view synthesis have shown impressive rendering quality. However, their speed is still limited when…

Diffusion models have recently achieved significant success in various image manipulation tasks, including image super-resolution and perceptual quality enhancement. Pretrained text-to-image models, such as Stable Diffusion, have exhibited…