Related papers: Optical Flow Representation Alignment Mamba Diffus…

The recent surge in the popularity of diffusion models for image synthesis has attracted new attention to their potential for generation tasks in other domains. However, their applications to symbolic music generation remain largely…

Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issues not only limit visibility but also degrade automatic tasks like detection.…

Video composition is the core task of video editing. Although image composition based on diffusion models has been highly successful, it is not straightforward to extend the achievement to video object composition tasks, which not only…

Video super-resolution remains a major challenge in low-level vision tasks. To date, CNN- and Transformer-based methods have delivered impressive results. However, CNNs are limited by local receptive fields, while Transformers struggle with…

The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called…

Since the era of deep learning, convolutional neural networks (CNNs) and vision transformers (ViTs) have been extensively studied and widely used in medical image classification tasks. Unfortunately, CNN's limitations in modeling long-range…

Medical time series, such as electrocardiograms (ECG) and electroencephalograms (EEG), exhibit complex temporal dynamics and structured cross-channel dependencies, posing fundamental challenges for automated analysis. Conventional…

Generating visual instructions in a given context is essential for developing interactive world simulators. While prior works address this problem through either text-guided image manipulation or video prediction, these tasks are typically…

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…

Co-speech gesture generation is crucial for producing synchronized and realistic human gestures that accompany speech, enhancing the animation of lifelike avatars in virtual environments. While diffusion models have shown impressive…

Fundus imaging is a critical tool in ophthalmology, with different imaging modalities offering unique advantages. For instance, fundus fluorescein angiography (FFA) can accurately identify eye diseases. However, traditional invasive FFA…

Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitivity to it, and the difficulty of accurately describing it.…

Image fusion integrates complementary information from different modalities to generate high-quality fused images, thereby enhancing downstream tasks such as object detection and semantic segmentation. Unlike task-specific techniques that…

The advent of Transformer and Mamba-based architectures has significantly advanced 3D medical image segmentation by enabling global contextual modeling, a capability traditionally limited in Convolutional Neural Networks (CNNs). However,…

Generating high-dimensional visual modalities is a computationally intensive task. A common solution is progressive generation, where the outputs are synthesized in a coarse-to-fine spectral autoregressive manner. While diffusion models…

Recently, the Mamba architecture has demonstrated significant successes in various computer vision tasks, such as classification and segmentation. However, its application to optical flow estimation remains unexplored. In this paper, we…

We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion mainly relies on several components for acceleration: (1)…

Video super-resolution (VSR) seeks to reconstruct high-resolution frames from low-resolution inputs. While diffusion-based methods have substantially improved perceptual quality, extending them to video remains challenging for two reasons:…

With recent advances of AIGC, video generation have gained a surge of research interest in both academia and industry (e.g., Sora). However, it remains a challenge to produce temporally aligned audio to synchronize the generated video,…

Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences and high resolutions computationally expensive. While…