Related papers: UltraZoom: Generating Gigapixel Images from Regula…
Self-captured full-body videos are popular, but most deployments require mounted cameras, carefully-framed shots, and repeated practice. We propose a more convenient solution that enables full-body video capture using handheld mobile…
High-resolution content creation is rapidly emerging as a central challenge in both the vision and graphics communities. Images serve as the most fundamental modality for visual expression, and content generation that aligns with the user…
We present VIDIM, a generative model for video interpolation, which creates short videos given a start and end frame. In order to achieve high fidelity and generate motions unseen in the input data, VIDIM uses cascaded diffusion models to…
Ultrafast single-shot imaging techniques now reach frame rates of tens of tera-frame-per-second (Tfps) and long sequence depths but are often too complex for large-scale use, both in terms of image acquisition and reconstruction. We propose…
As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect…
We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training…
Diffusion models have emerged as the leading approach for image synthesis, demonstrating exceptional photorealism and diversity. However, training diffusion models at high resolutions remains computationally prohibitive, and existing…
Image zooming is the process of enlarging the spatial resolution of a given digital image. We present a novel technique that intelligently modifies the classical pixel replication method for zooming. Our method decomposes a given image into…
Image super-resolution (SR) is a field in computer vision that focuses on reconstructing high-resolution images from the respective low-resolution image. However, super-resolution is a well-known ill-posed problem as most methods rely on…
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…
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is…
Sparse-view reconstruction models typically require precise camera poses, yet obtaining these parameters from sparse-view images remains challenging. We introduce FreeSplatter, a scalable feed-forward framework that generates high-quality…
Super Resolution is the problem of recovering a high-resolution image from a single or multiple low-resolution images of the same scene. It is an ill-posed problem since high frequency visual details of the scene are completely lost in…
Previous works leveraging video models for image-to-3D scene generation tend to suffer from geometric distortions and blurry content. In this paper, we renovate the pipeline of image-to-3D scene generation by unlocking the potential of…
Automatically generating a complete 3D scene from a text description, a reference image, or both has significant applications in fields like virtual reality and gaming. However, current methods often generate low-quality textures and…
Thumbnails are widely used all over the world as a preview for digital images. In this work we propose a deep neural framework to generate thumbnails of any size and aspect ratio, even for unseen values during training, with high accuracy…
Benefited from the deep learning, image Super-Resolution has been one of the most developing research fields in computer vision. Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image…
A simple method of constructing the 3D surface of non-transparent micro-objects by extending the depth-of-field on the whole attainable surface is presented. The series of images of a sample are recorded by the sequential movement of the…
Superpixels are a useful representation to reduce the complexity of image data. However, to combine superpixels with convolutional neural networks (CNNs) in an end-to-end fashion, one requires extra models to generate superpixels and…
Event cameras capture the world at high time resolution and with minimal bandwidth requirements. However, event streams, which only encode changes in brightness, do not contain sufficient scene information to support a wide variety of…