Related papers: Semantic Latent Decomposition with Normalizing Flo…

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

Understanding the world around us and making decisions about the future is a critical component to human intelligence. As autonomous systems continue to develop, their ability to reason about the future will be the key to their success.…

Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adversarial Networks (GANs) have increasingly been used in…

Continuous diffusion has been the foundation of high-fidelity, controllable, and few-step generation of many data modalities such as images. However, in language modeling, prior continuous diffusion language models (DLMs) lag behind…

StyleGAN has achieved great progress in 2D face reconstruction and semantic editing via image inversion and latent editing. While studies over extending 2D StyleGAN to 3D faces have emerged, a corresponding generic 3D GAN inversion…

Generating and manipulating human facial images using high-level attributal controls are important and interesting problems. The models proposed in previous work can solve one of these two problems (generation or manipulation), but not both…

Recent advances in flow-based generative models have enabled training-free, text-guided image editing by inverting an image into its latent noise and regenerating it under a new target conditional guidance. However, existing methods…

Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models…

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…

Text-to-image diffusion models have revolutionized image synthesis and editing, but precise control over stylistic attributes remains a challenge, often causing unintended content modifications. We propose an approach for fine-grained…

Video deblurring is a challenging task due to the spatially variant blur caused by camera shake, object motions, and depth variations, etc. Existing methods usually estimate optical flow in the blurry video to align consecutive frames or…

In this work, we propose a semantic flow-guided two-stage framework for shape-aware face swapping, namely FlowFace. Unlike most previous methods that focus on transferring the source inner facial features but neglect facial contours, our…

Efficient encoding of network flow spaces while preserving spatial locality is essential for intelligent Software-Defined Networking (SDN) applications, particularly those employing reinforcement learning (RL) methods in a reactive manner.…

While the quality of GAN image synthesis has improved tremendously in recent years, our ability to control and condition the output is still limited. Focusing on StyleGAN, we introduce a simple and effective method for making local,…

Rectified flow models have emerged as a dominant approach in image generation, showcasing impressive capabilities in high-quality image synthesis. However, despite their effectiveness in visual generation, rectified flow models often…

Underwater Salient Object Detection (USOD) faces significant challenges, including underwater image quality degradation and domain gaps. Existing methods tend to ignore the physical principles of underwater imaging or simply treat…

Recently, a surge of advanced facial editing techniques have been proposed that leverage the generative power of a pre-trained StyleGAN. To successfully edit an image this way, one must first project (or invert) the image into the…

In this paper, we show that slow feature analysis (SFA), a common time series decomposition method, naturally fits into the flow-based models (FBM) framework, a type of invertible neural latent variable models. Building upon recent advances…

AI-driven image generation has improved significantly in recent years. Generative adversarial networks (GANs), like StyleGAN, are able to generate high-quality realistic data and have artistic control over the output, as well. In this work,…

Existing facial editing methods have achieved remarkable results, yet they often fall short in supporting multimodal conditional local facial editing. One of the significant evidences is that their output image quality degrades dramatically…