Related papers: HiCAST: Highly Customized Arbitrary Style Transfer…

Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers…

Artistic styles are defined by both their structural and appearance elements. Existing neural stylization techniques primarily focus on transferring appearance-level features such as color and texture, often neglecting the equally crucial…

Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world…

Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion.Recent advances in diffusion models have enabled significant…

Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align text and motion latent spaces but sacrifice expressiveness;…

Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training…

While current research predominantly focuses on image-based colorization, the domain of video-based colorization remains relatively unexplored. Most existing video colorization techniques operate on a frame-by-frame basis, often overlooking…

We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our method preserves the generative power of pretrained diffusion…

Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation…

Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution,…

Novel architectures have recently improved generative image synthesis leading to excellent visual quality in various tasks. Of particular note is the field of ``AI-Art'', which has seen unprecedented growth with the emergence of powerful…

State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a…

Style transfer algorithms strive to render the content of one image using the style of another. We propose Style Transfer by Relaxed Optimal Transport and Self-Similarity (STROTSS), a new optimization-based style transfer algorithm. We…

Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational burden of the diffusion process. While recent advancements…

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

Deep generative models are now able to synthesize high-quality audio signals, shifting the critical aspect in their development from audio quality to control capabilities. Although text-to-music generation is getting largely adopted by the…

In light of the widespread application of Automatic Speech Recognition (ASR) systems, their security concerns have received much more attention than ever before, primarily due to the susceptibility of Deep Neural Networks. Previous studies…

Stain normalization algorithms aim to transform the color and intensity characteristics of a source multi-gigapixel histology image to match those of a target image, mitigating inconsistencies in the appearance of stains used to highlight…

Audio classification models, particularly the Audio Spectrogram Transformer (AST), play a crucial role in efficient audio analysis. However, optimizing their efficiency without compromising accuracy remains a challenge. In this paper, we…

Artistic style transfer aims to create new artistic images by rendering a given photograph with the target artistic style. Existing methods learn styles simply based on global statistics or local patches, lacking careful consideration of…