Search Results for author:
Found 11 papers, 8 papers with code
Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation
Co-speech gesture generation is crucial for creating lifelike avatars and enhancing human-computer interactions by synchronizing gestures with speech.
Ranked #2 on
Gesture Generation
on BEAT2
GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling
To overcome the suboptimal performance of flow matching baseline, we propose latent shortcut learning and beta distribution time stamp sampling during training to enhance gesture synthesis quality and accelerate inference.
Ranked #1 on
Gesture Generation
on BEAT2
Generative AI for Cel-Animation: A Survey
Traditional Celluloid (Cel) Animation production pipeline encompasses multiple essential steps, including storyboarding, layout design, keyframe animation, inbetweening, and colorization, which demand substantial manual effort, technical expertise, and significant time investment.
KinMo: Kinematic-aware Human Motion Understanding and Generation
Current human motion synthesis frameworks rely on global action descriptions, creating a modality gap that limits both motion understanding and generation capabilities.
TextToon: Real-Time Text Toonify Head Avatar from Single Video
Given a short monocular video sequence and a written instruction about the avatar style, our model can generate a high-fidelity toonified avatar that can be driven in real-time by another video with arbitrary identities.
Articulatory Phonetics Informed Controllable Expressive Speech Synthesis
We open-source the dataset and TTS models.
An Empirical Analysis on Large Language Models in Debate Evaluation
In this study, we investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3. 5 and GPT-4 in the context of debate evaluation.
Adaptive Super Resolution For One-Shot Talking-Head Generation
In this work, we propose an adaptive high-quality talking-head video generation method, which synthesizes high-resolution video without additional pre-trained modules.
GaussianStyle: Gaussian Head Avatar via StyleGAN
Existing methods like Neural Radiation Fields (NeRF) and 3D Gaussian Splatting (3DGS) have made significant strides in facial attribute control such as facial animation and components editing, yet they struggle with fine-grained representation and scalability in dynamic head modeling.
Tri$^{2}$-plane: Thinking Head Avatar via Feature Pyramid
Recent years have witnessed considerable achievements in facial avatar reconstruction with neural volume rendering.
Video Understanding with Large Language Models: A Survey
With the burgeoning growth of online video platforms and the escalating volume of video content, the demand for proficient video understanding tools has intensified markedly.
