相关论文: JambaTalk: Speech-Driven 3D Talking Head Generatio…

In this paper, we present TalkingMachines -- an efficient framework that transforms pretrained video generation models into real-time, audio-driven character animators. TalkingMachines enables natural conversational experiences by…

World models, which simulate environmental dynamics and generate sensor observations, are gaining increasing attention in autonomous driving. However, progress in LiDAR-based world models has lagged behind those built on camera videos or…

Brain tumors exhibit high heterogeneity in morphology and multimodal contrast, making manual slice-by-slice de lineation time-consuming and experience-dependent, thus necessitating efficient and stable automated segmentation methods. To…

Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…

Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging. Recent advancements in state space models (SSMs), notably Mamba, have…

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…

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)…

Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for this task. However, their mere aggregation does not lead to…

Long-duration talking video synthesis faces enduring challenges in achieving high video quality, portrait consistency, temporal coherence, and computational efficiency. As video length increases, issues such as visual degradation, portrait…

State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models grow increasingly larger, the need for Parameter-Efficient…

Generating synchronized and natural lip movement with speech is one of the most important tasks in creating realistic virtual characters. In this paper, we present a combined deep neural network of one-dimensional convolutions and LSTM to…

Text-to-motion generation, which converts motion language descriptions into coherent 3D human motion sequences, has attracted increasing attention in fields, such as avatar animation and humanoid robotic interaction. Though existing models…

Transformers have proven effective in language modeling but are limited by high computational and memory demands that grow quadratically with input sequence length. State space models (SSMs) offer a promising alternative by reducing…

Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…

Emotional talking head generation has attracted growing attention. Previous methods, which are mainly GAN-based, still struggle to consistently produce satisfactory results across diverse emotions and cannot conveniently specify…

Expressions are fundamental to conveying human emotions. With the rapid advancement of AI-generated content (AIGC), realistic and expressive 3D facial animation has become increasingly crucial. Despite recent progress in speech-driven…

This paper introduces VMatcher, a hybrid Mamba-Transformer network for semi-dense feature matching between image pairs. Learning-based feature matching methods, whether detector-based or detector-free, achieve state-of-the-art performance…

Generating realistic dyadic human motion from text descriptions presents significant challenges, particularly for extended interactions that exceed typical training sequence lengths. While recent transformer-based approaches have shown…

In recent years, deep learning has shown near-expert performance in segmenting complex medical tissues and tumors. However, existing models are often task-specific, with performance varying across modalities and anatomical regions.…

Multimodal Large Language Models (MLLMs) have attracted much attention for their multifunctionality. However, traditional Transformer architectures incur significant overhead due to their secondary computational complexity. To address this…