Related papers: Unsupervised Decomposition and Recombination with …

Unsupervised landmark learning is the task of learning semantic keypoint-like representations without the use of expensive input keypoint-level annotations. A popular approach is to factorize an image into a pose and appearance data stream,…

We present PartComposer: a framework for part-level concept learning from single-image examples that enables text-to-image diffusion models to compose novel objects from meaningful components. Existing methods either struggle with…

We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to…

Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to…

Diffusion models have achieved remarkable success in generating high quality image and video data. More recently, they have also been used for image compression with high perceptual quality. In this paper, we present a novel approach to…

Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning…

Identifying important components or factors in large amounts of noisy data is a key problem in machine learning and data mining. Motivated by a pattern decomposition problem in materials discovery, aimed at discovering new materials for…

Images can be viewed as layered compositions, foreground objects over background, with potential occlusions. This layered representation enables independent editing of elements, offering greater flexibility for content creation. Despite the…

Diffusion models have emerged as powerful generative approaches for missing-data imputation, yet most existing methods operate directly in data space and degrade when training data are heavily incomplete. We investigate whether shifting…

Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently…

Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling the generative process using highly compact conditioning signals. In this work,…

Generative diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. In favor of their ability to supplement missing details and generate aesthetically pleasing contents, recent works have…

Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. While prior works have addressed unsupervised image segmentation, they significantly lag behind supervised models. In…

Diffusion models have emerged as state-of-the-art generative methods for image synthesis, yet their potential as general-purpose feature encoders remains underexplored. Trained for denoising and generation without labels, they can be…

For learned image representations, basic autoencoders often produce blurry results. Reconstruction quality can be improved by incorporating additional penalties such as adversarial (GAN) and perceptual losses. Arguably, these approaches…

Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score matching, which can…

We propose a learning-based framework for disentangling outdoor scenes into temporally-varying illumination and permanent scene factors. Inspired by the classic intrinsic image decomposition, our learning signal builds upon two insights: 1)…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks simultaneously. We…

We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models. Contrary to recent approaches that model image layers with autoencoder networks, we represent them as explicit…

Generative models have demonstrated strong performance in conditional settings and can be viewed as a form of data compression, where the condition serves as a compact representation. However, their limited controllability and…