Related papers: DIP: Unsupervised Dense In-Context Post-training o…

Recent advances in vision language pretraining (VLP) have been largely attributed to the large-scale data collected from the web. However, uncurated dataset contains weakly correlated image-text pairs, causing data inefficiency. To address…

Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations…

We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a "noise-to-map" generative paradigm for prediction by progressively removing noise from a…

Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)? In this paper, we present a simple yet surprisingly powerful…

Recent video inpainting methods have achieved encouraging improvements by leveraging optical flow to guide pixel propagation from reference frames either in the image space or feature space. However, they would produce severe artifacts in…

Self-supervised vision transformers (SSTs) have shown great potential to yield rich localization maps that highlight different objects in an image. However, these maps remain class-agnostic since the model is unsupervised. They often tend…

Nowadays, scene text recognition has attracted more and more attention due to its diverse applications. Most state-of-the-art methods adopt an encoder-decoder framework with the attention mechanism, autoregressively generating text from…

Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. In recent years, solutions that are based on deep Convolutional Neural Networks (CNNs) have shown great promise. Yet, most of…

We extend the Deep Image Prior (DIP) framework to one-dimensional signals. DIP is using a randomly initialized convolutional neural network (CNN) to solve linear inverse problems by optimizing over weights to fit the observed measurements.…

Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret discrete representations, due to the difficulty of…

We present a framework to translate between 2D image views and 3D object shapes. Recent progress in deep learning enabled us to learn structure-aware representations from a scene. However, the existing literature assumes that pairs of…

The de-facto approach to many vision tasks is to start from pretrained visual representations, typically learned via supervised training on ImageNet. Recent methods have explored unsupervised pretraining to scale to vast quantities of…

Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality. Most existing methods rely on human supervision or parameter retraining, both of which…

Image Transformer has recently achieved significant progress for natural image understanding, either using supervised (ViT, DeiT, etc.) or self-supervised (BEiT, MAE, etc.) pre-training techniques. In this paper, we propose \textbf{DiT}, a…

Objective: To propose and validate an unsupervised MRI reconstruction method that does not require fully sampled k-space data. Materials and Methods: The proposed method, deep image prior with structured sparsity (DISCUS), extends the deep…

We present a perceptually-driven video compression framework integrating implicit neural representations (INRs) and pre-trained video diffusion models to address the extremely low bitrate regime (<0.05 bpp). Our approach exploits the…

Imitation learning has proven to be a powerful tool for training complex visuomotor policies. However, current methods often require hundreds to thousands of expert demonstrations to handle high-dimensional visual observations. A key reason…

Blind video decaptioning is a problem of automatically removing text overlays and inpainting the occluded parts in videos without any input masks. While recent deep learning based inpainting methods deal with a single image and mostly…

We propose a novel unsupervised backlit image enhancement method, abbreviated as CLIP-LIT, by exploring the potential of Contrastive Language-Image Pre-Training (CLIP) for pixel-level image enhancement. We show that the open-world CLIP…

Image restoration, which aims to retrieve and enhance degraded images, is fundamental across a wide range of applications. While conventional deep learning approaches have notably improved the image quality across various tasks, they still…