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

Deep image prior (DIP) proposed in recent research has revealed the inherent trait of convolutional neural networks (CNN) for capturing substantial low-level image statistics priors. This framework efficiently addresses the inverse problems…

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional…

The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for…

Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that…

Deep learning (DL) methods have been extensively applied to various image recovery problems, including magnetic resonance imaging (MRI) and computed tomography (CT) reconstruction. Beyond supervised models, other approaches have been…

Diffusion inversion is a task of recovering the noise of an image in a diffusion model, which is vital for controllable diffusion image editing. At present, diffusion inversion still remains a challenging task due to the lack of viable…

This paper proposes a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. While self-supervised pre-training approaches, e.g., Masked Autoencoder, have shown success in…

This paper investigates the application of unsupervised learning methods for computed tomography (CT) reconstruction. To motivate our work, we review several existing priors, namely the truncated Gaussian prior, the $l_1$ prior, the total…

Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially…

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite…

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible…

Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP),…

Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks based on features extracted from diverse views of the data.…

We propose DepR, a depth-guided single-view scene reconstruction framework that integrates instance-level diffusion within a compositional paradigm. Instead of reconstructing the entire scene holistically, DepR generates individual objects…

Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are…

The ability to classify images is dependent on having access to large labeled datasets and testing on data from the same domain that the model can train on. Classification becomes more challenging when dealing with new data from a different…

Deep image prior (DIP), which utilizes a deep convolutional network (ConvNet) structure itself as an image prior, has attracted attentions in computer vision and machine learning communities. It empirically shows the effectiveness of…

Extracting informative representations from videos is fundamental for effectively learning various downstream tasks. We present a novel approach for unsupervised learning of meaningful representations from videos, leveraging the concept of…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space, and a decoder maps the generated latents back to pixels. Yet the latent-to-pixel…