Related papers: Exploring the latent space of diffusion models dir…
Despite the success of diffusion models (DMs), we still lack a thorough understanding of their latent space. To understand the latent space $\mathbf{x}_t \in \mathcal{X}$, we analyze them from a geometrical perspective. Our approach…
Diffusion models generate images with an unprecedented level of quality, but how can we freely rearrange image layouts? Recent works generate controllable scenes via learning spatially disentangled latent codes, but these methods do not…
Existing latent diffusion models typically couple scale with content complexity, using more latent tokens to represent higher-resolution images or higher-frame rate videos. However, the latent capacity required to represent visual data…
Recent advances in image editing leverage latent diffusion models (LDMs) for versatile, text-prompt-driven edits across diverse tasks. Yet, maintaining pixel-level edge structures-crucial for tasks such as photorealistic style transfer or…
Text-to-image diffusion models have demonstrated a remarkable ability to generate photorealistic images from natural language prompts. These high-resolution, language-guided synthesized images are essential for the explainability of disease…
Diffusion models have recently been investigated as powerful generative solvers for image dehazing, owing to their remarkable capability to model the data distribution. However, the massive computational burden imposed by the retraining of…
Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of generated images, remain…
Recent advancements in learning latent codes derived from high-dimensional shapes have demonstrated impressive outcomes in 3D generative modeling. Traditionally, these approaches employ a trained autoencoder to acquire a continuous implicit…
Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality and generation speed. MDMs denoise by progressively…
Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…
Deep neural networks used for image classification often use convolutional filters to extract distinguishing features before passing them to a linear classifier. Most interpretability literature focuses on providing semantic meaning to…
Diffusion Transformers (DiTs) have recently achieved remarkable success in text-guided image generation. In image editing, DiTs project text and image inputs to a joint latent space, from which they decode and synthesize new images.…
Diffusion Transformer (DiT) models have achieved unprecedented quality in image and video generation, yet their iterative sampling process remains computationally prohibitive. To accelerate inference, feature caching methods have emerged by…
Disentangling content and style from a single image, known as content-style decomposition (CSD), enables recontextualization of extracted content and stylization of extracted styles, offering greater creative flexibility in visual…
Diffusion models emerged as a leading approach in text-to-image generation, producing high-quality images from textual descriptions. However, attempting to achieve detailed control to get a desired image solely through text remains a…
Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…
The traditional method of computing singular value decomposition (SVD) of a data matrix is based on a least squares principle, thus, is very sensitive to the presence of outliers. Hence the resulting inferences across different applications…
Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural, we often aim to optimize downstream reward functions while…
The correspondence between input text and the generated image exhibits opacity, wherein minor textual modifications can induce substantial deviations in the generated image. While, text embedding, as the pivotal intermediary between text…
Recent advances in the field of generative models and in particular generative adversarial networks (GANs) have lead to substantial progress for controlled image editing, especially compared with the pre-deep learning era. Despite their…