相关论文: EasyVFX: Frequency-Driven Decoupling for Resource-…
A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…
Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…
Long-sequence video diffusion transformers hit a quadratic self-attention cost that dominates runtime and memory for very long token sequences. Most efficient attention methods use one approximation everywhere, yet video features are…
Recent video diffusion models generate photorealistic, temporally coherent videos, yet they fall short as reliable world models for autonomous driving, where structured motion and physically consistent interactions are essential. Adapting…
In recent years, the global demand for high-resolution videos and the emergence of new multimedia applications have created the need for a new video coding standard. Hence, in July 2020 the Versatile Video Coding (VVC) standard was released…
The ultimate goal of video generation is to satisfy a fundamental trilemma: achieving high visual quality, maintaining rigorous physical consistency, and enabling precise controllability. While recent models can maintain this balance in…
The rapid progression of generative AI (GenAI) technologies has heightened concerns regarding the misuse of AI-generated imagery. To address this issue, robust detection methods have emerged as particularly compelling, especially in…
Learning based video compression attracts increasing attention in the past few years. The previous hybrid coding approaches rely on pixel space operations to reduce spatial and temporal redundancy, which may suffer from inaccurate motion…
Emotional voice conversion (VC) aims to convert a neutral voice to an emotional (e.g. happy) one while retaining the linguistic information and speaker identity. We note that the decoupling of emotional features from other speech…
Video diffusion models have made substantial progress in various video generation applications. However, training models for long video generation tasks require significant computational and data resources, posing a challenge to developing…
Automatic font generation based on deep learning has aroused a lot of interest in the last decade. However, only a few recently-reported approaches are capable of directly generating vector glyphs and their results are still far from…
Learning effective visuomotor policies for robotic manipulation is challenging, as it requires generating precise actions while maintaining computational efficiency. Existing methods remain unsatisfactory due to inherent limitations in the…
Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space, becoming a key component of most Latent Video Diffusion Models (LVDMs) to reduce model training costs. However, as the resolution and duration of…
The generation of high-fidelity view synthesis is essential for robotic navigation and interaction but remains challenging, particularly in indoor environments and real-time scenarios. Existing techniques often require significant…
Ultra-high-resolution image synthesis holds significant potential, yet remains an underexplored challenge due to the absence of standardized benchmarks and computational constraints. In this paper, we establish Aesthetic-4K, a meticulously…
Ultrasound (US) is widely used for its advantages of real-time imaging, radiation-free and portability. In clinical practice, analysis and diagnosis often rely on US sequences rather than a single image to obtain dynamic anatomical…
Human motion is a key function to communicate information. In the application, short-form mobile video is so popular all over the world such as Tik Tok. The users would like to add more VFX so as to pursue creativity and personlity. Many…
Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, causal modelling, and operator training become approachable…
Generative Face Video Coding (GFVC) achieves superior rate-distortion performance by leveraging the strong inference capabilities of deep generative models. However, its practical deployment is hindered by large model parameters and high…
Recent mesh generation approaches typically tokenize triangle meshes into sequences of tokens and train autoregressive models to generate these tokens sequentially. Despite substantial progress, such token sequences inevitably reuse…