相关论文: Addressing Text Embedding Leakage in Diffusion-bas…
Expressive neural text-to-speech (TTS) systems incorporate a style encoder to learn a latent embedding as the style information. However, this embedding process may encode redundant textual information. This phenomenon is called content…
Recent advancements in language-guided diffusion models for image editing are often bottle-necked by cumbersome prompt engineering to precisely articulate desired changes. An intuitive alternative calls on guidance from in-the-wild image…
Standard Adjacency Spectral Embedding (ASE) relies on a global low-rank assumption often incompatible with the sparse, transitive structure of real-world networks, causing local geometric features to be 'smeared'. To address this, we…
Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation,…
Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attempted to obtain generation-friendly VAEs by directly adopting…
Current diffusion-based video editing primarily focuses on local editing (\textit{e.g.,} object/background editing) or global style editing by utilizing various dense correspondences. However, these methods often fail to accurately edit the…
Recent advances in diffusion models have enabled high-quality generation and manipulation of images guided by texts, as well as concept learning from images. However, naive applications of existing methods to editing tasks that require…
Text-guided diffusion models have significantly advanced image editing, enabling highly realistic and local modifications based on textual prompts. While these developments expand creative possibilities, their malicious use poses…
Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…
With the development of diffusion-based customization methods like DreamBooth, individuals now have access to train the models that can generate their personalized images. Despite the convenience, malicious users have misused these…
Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their…
Image aesthetic enhancement aims to perceive aesthetic deficiencies in images and perform corresponding editing operations, which is highly challenging and requires the model to possess creativity and aesthetic perception capabilities.…
Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode text and reference images separately. This limits…
Latent Diffusion Models (LDMs) have markedly advanced the quality of image inpainting and local editing. However, the inherent latent compression often introduces pixel-level inconsistencies, such as chromatic shifts, texture mismatches,…
Editing real images using a pre-trained text-to-image (T2I) diffusion/flow model often involves inverting the image into its corresponding noise map. However, inversion by itself is typically insufficient for obtaining satisfactory results,…
Diffusion models excel at image generation. Recent studies have shown that these models not only generate high-quality images but also encode text-image alignment information through attention maps or loss functions. This information is…
Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing…
Diffusion models have made significant advances in text-guided synthesis tasks. However, editing user-provided images remains challenging, as the high dimensional noise input space of diffusion models is not naturally suited for image…
Current diffusion models create photorealistic images given a text prompt as input but struggle to correctly bind attributes mentioned in the text to the right objects in the image. This is evidenced by our novel image-graph alignment model…
Recent advances in text-to-image (T2I) diffusion models have enabled remarkable control over various attributes, yet precise color specification remains a fundamental challenge. Existing approaches, such as ColorPeel, rely on model…