相关论文: Causal-Adapter: Taming Text-to-Image Diffusion for…

Counterfactual image generation presents significant challenges, including preserving identity, maintaining perceptual quality, and ensuring faithfulness to an underlying causal model. While existing auto-encoding frameworks admit semantic…

Diffusion probabilistic models (DPMs) have become the state-of-the-art in high-quality image generation. However, DPMs have an arbitrary noisy latent space with no interpretable or controllable semantics. Although there has been significant…

Prompt learning has garnered attention for its efficiency over traditional model training and fine-tuning. However, existing methods, constrained by inadequate theoretical foundations, encounter difficulties in achieving causally invariant…

Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descriptions. However, these models often struggle with achieving…

Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities. However, training these models is resource-intensive, and…

With the growing popularity of personalized human content creation and sharing, there is a rising demand for advanced techniques in customized human image generation. However, current methods struggle to simultaneously maintain the fidelity…

Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have…

Recent advancements in diffusion models have showcased their impressive capacity to generate visually striking images. Nevertheless, ensuring a close match between the generated image and the given prompt remains a persistent challenge. In…

Text-to-Image (T2I) Diffusion Models have achieved remarkable performance in generating high quality images. However, enabling precise control of continuous attributes, especially multiple attributes simultaneously, in a new domain (e.g.,…

Physical and optical factors interacting with sensor characteristics create complex image degradation patterns. Despite advances in deep learning-based super-resolution, existing methods overlook the causal nature of degradation by adopting…

The remarkable advancement in text-to-image generation models significantly boosts the research in ID customization generation. However, existing personalization methods cannot simultaneously satisfy high fidelity and high-efficiency…

Causal generative modelling is gaining interest in medical imaging due to its ability to answer interventional and counterfactual queries. Most work focuses on generating counterfactual images that look plausible, using auxiliary…

Diffusion-based generative image compression has demonstrated remarkable potential for achieving realistic reconstruction at ultra-low bitrates. The key to unlocking this potential lies in making the entire compression process…

Adapting text-to-image (T2I) latent diffusion models (LDMs) to video editing has shown strong visual fidelity and controllability, but challenges remain in maintaining causal relationships inherent to the video data generating process.…

Layout-to-image generation refers to the task of synthesizing photo-realistic images based on semantic layouts. In this paper, we propose LayoutDiffuse that adapts a foundational diffusion model pretrained on large-scale image or text-image…

Counterfactual image editing is an important task in generative AI, which asks how an image would look if certain features were different. The current literature on the topic focuses primarily on changing individual features while remaining…

Recent advancement in text-to-image models (e.g., Stable Diffusion) and corresponding personalized technologies (e.g., DreamBooth and LoRA) enables individuals to generate high-quality and imaginative images. However, they often suffer from…

Recent advances in generative motion synthesis have enabled the production of realistic human motions from diverse input modalities. However, synthesizing compound actions from texts, which integrate multiple concurrent actions into…

We introduce Causal Diffusion as the autoregressive (AR) counterpart of Diffusion models. It is a next-token(s) forecasting framework that is friendly to both discrete and continuous modalities and compatible with existing next-token…

Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-dimensional latent variable space. However, few existing…