Related papers: Draft-and-Revise: Effective Image Generation with …
Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of lossy image compression from the perspective of generative…
Image super-resolution (SR) techniques are used to generate a high-resolution image from a low-resolution image. Until now, deep generative models such as autoregressive models and Generative Adversarial Networks (GANs) have proven to be…
Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant…
The task of image-to-multi-view generation refers to generating novel views of an instance from a single image. Recent methods achieve this by extending text-to-image latent diffusion models to multi-view version, which contains an VAE…
To truly understand the visual world our models should be able not only to recognize images but also generate them. To this end, there has been exciting recent progress on generating images from natural language descriptions. These methods…
Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the…
The current models of image representation based on Convolutional Neural Networks (CNN) have shown tremendous performance in image retrieval. Such models are inspired by the information flow along the visual pathway in the human visual…
We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…
High-dimensional generative models have many applications including image compression, multimedia generation, anomaly detection and data completion. State-of-the-art estimators for natural images are autoregressive, decomposing the joint…
In today's world, image processing plays a crucial role across various fields, from scientific research to industrial applications. But one particularly exciting application is image captioning. The potential impact of effective image…
In the framework of learned image compression, the context model plays a pivotal role in capturing the dependencies among latent representations. To reduce the decoding time resulting from the serial autoregressive context model, the…
We introduce Contextual Vision Transformers (ContextViT), a method designed to generate robust image representations for datasets experiencing shifts in latent factors across various groups. Derived from the concept of in-context learning,…
Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the quantization strategy for better reconstruction quality,…
An ongoing trend in generative modelling research has been to push sample resolutions higher whilst simultaneously reducing computational requirements for training and sampling. We aim to push this trend further via the combination of…
Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient…
Unlike conventional person re-identification (ReID), clothes-changing ReID (CC-ReID) presents severe challenges due to substantial appearance variations introduced by clothing changes. In this work, we propose the Quality-Aware Dual-Branch…
Given an image dataset, we are often interested in finding data generative factors that encode semantic content independently from pose variables such as rotation and translation. However, current disentanglement approaches do not impose…
Image enhancement models for mobile devices often struggle to balance high output quality with the fast processing speeds required by mobile hardware. While recent deep learning models can enhance low-quality mobile photos into high-quality…
Recent breakthroughs in video autoencoders (Video AEs) have advanced video generation, but existing methods fail to efficiently model spatio-temporal redundancies in dynamics, resulting in suboptimal compression factors. This shortfall…
Continuous diffusion and flow models are attractive for non-autoregressive text generation because they can update all positions in parallel. A major difficulty is the interface between continuous latent states and discrete tokens. This…