Related papers: Unsupervised Decomposition and Recombination with …

Image composition and generation are processes where the artists need control over various parts of the generated images. However, the current state-of-the-art generation models, like Stable Diffusion, cannot handle fine-grained part-level…

We present a novel perspective on learning video embedders for generative modeling: rather than requiring an exact reproduction of an input video, an effective embedder should focus on synthesizing visually plausible reconstructions. This…

We introduce a new framework for unsupervised learning of representations based on a novel hierarchical decomposition of information. Intuitively, data is passed through a series of progressively fine-grained sieves. Each layer of the sieve…

This paper presents a novel theoretical framework for understanding how diffusion models can learn disentangled representations. Within this framework, we establish identifiability conditions for general disentangled latent variable models,…

This paper studies linear reconstruction of partially observed functional data which are recorded on a discrete grid. We propose a novel estimation approach based on approximate factor models with increasing rank taking into account…

Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, potentially multimodal data distribution into a single…

We propose a data-driven approach for intrinsic image decomposition, which is the process of inferring the confounding factors of reflectance and shading in an image. We pose this as a two-stage learning problem. First, we train a model to…

Deep learning-based image generation has seen significant advancements with diffusion models, notably improving the quality of generated images. Despite these developments, generating images with unseen characteristics beneficial for…

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…

We explore recurrent encoder multi-decoder neural network architectures for semi-supervised sequence classification and reconstruction. We find that the use of multiple reconstruction modules helps models generalize in a classification task…

In this work, we explore an untapped signal in diffusion model inference. While all previous methods generate images independently at inference, we instead ask if samples can be generated collaboratively. We propose Group Diffusion,…

Blind face restoration methods have shown remarkable performance, particularly when trained on large-scale synthetic datasets with supervised learning. These datasets are often generated by simulating low-quality face images with a…

In this paper, we propose a diffusion-based unsupervised framework that incorporates physically explainable Retinex theory with diffusion models for low-light image enhancement, named LightenDiffusion. Specifically, we present a…

We present a new approach for representing and reconstructing multidimensional magnetic resonance imaging (MRI) data. Our method builds on a novel, learned feature-based image representation that disentangles different types of features,…

Representational learning forms the backbone of most deep learning applications, and the value of a learned representation is intimately tied to its information content regarding different factors of variation. Finding good representations…

We propose a novel unsupervised generative model that learns to disentangle object identity from other low-level aspects in class-imbalanced data. We first investigate the issues surrounding the assumptions about uniformity made by InfoGAN,…

As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference, while secondarily…

Diffusion-based image compression methods have achieved notable progress, delivering high perceptual quality at low bitrates. However, their practical deployment is hindered by significant inference latency and heavy computational overhead,…

Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements…

Building on the momentum of image generation diffusion models, there is an increasing interest in video-based diffusion models. However, video generation poses greater challenges due to its higher-dimensional nature, the scarcity of…