相关论文: CleanStyle: Plug-and-Play Style Conditioning Purif…

Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains. In this paper, we reexamine the SDS process and introduce a straightforward interpretation that demystifies the…

While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders…

Recently, the multimedia community has witnessed the rise of diffusion models trained on large-scale multi-modal data for visual content creation, particularly in the field of text-to-image generation. In this paper, we propose a new task…

CLIPStyler demonstrated image style transfer with realistic textures using only the style text description (instead of requiring a reference style image). However, the ground semantics of objects in style transfer output is lost due to…

This paper introduces a scalable paradigm for supervised style transfer by inverting the problem: instead of learning to stylize directly, we learn to destylize, reducing stylistic elements from artistic images to recover their natural…

The growing demand for rapid and scalable 3D asset creation has driven interest in feed-forward 3D reconstruction methods, with 3D Gaussian Splatting (3DGS) emerging as an effective scene representation. While recent approaches have…

In this pioneering study, we introduce StyleWallfacer, a groundbreaking unified training and inference framework, which not only addresses various issues encountered in the style transfer process of traditional methods but also unifies the…

Recent advances in Text-to-Image (T2I) diffusion models have transformed image generation, enabling significant progress in stylized generation using only a few style reference images. However, current diffusion-based methods struggle with…

Text-driven diffusion models have significantly advanced the image editing performance by using text prompts as inputs. One crucial step in text-driven image editing is to invert the original image into a latent noise code conditioned on…

Text autoencoders are commonly used for conditional generation tasks such as style transfer. We propose methods which are plug and play, where any pretrained autoencoder can be used, and only require learning a mapping within the…

Owing to the power of vision-language foundation models, e.g., CLIP, the area of image synthesis has seen recent important advances. Particularly, for style transfer, CLIP enables transferring more general and abstract styles without…

Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we…

Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability…

Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in designing models that perform plug-and-play generation, i.e., to use a…

Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlearning through erasure success; its impact on broader…

In this paper, we introduce MegaStyle, a novel and scalable data curation pipeline that constructs an intra-style consistent, inter-style diverse and high-quality style dataset. We achieve this by leveraging the consistent text-to-image…

Deep segmentation models that generalize to images with unknown appearance are important for real-world medical image analysis. Retraining models leads to high latency and complex pipelines, which are impractical in clinical settings. The…

Universal style transfer retains styles from reference images in content images. While existing methods have achieved state-of-the-art style transfer performance, they are not aware of the content leak phenomenon that the image content may…

Reference-based object composition involves integrating foreground reference image with background scene to produce harmonious fused image. This task becomes particularly challenging in cross-domain scenarios, where models must balance…

Navigating in the latent space of StyleGAN has shown effectiveness for face editing. However, the resulting methods usually encounter challenges in complicated navigation due to the entanglement among different attributes in the latent…