papers

Publications (13)

cs.CV2026

DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation

Yichen Peng, Jyun-Ting Song, Siyeol Jung +7

Generating realistic conversational gestures are essential for achieving natural, socially engaging interactions with digital humans. However, existing methods typically map a sing…

cs.CV2026

UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking

Xuangeng Chu, Ruicong Liu, Yifei Huang +3

Generating lifelike conversational avatars requires modeling not just isolated speakers, but the dynamic, reciprocal interaction of speaking and listening. However, modeling the li…

cs.CV2024

LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model

Xi Wang, Hongzhen Li, Heng Fang +4

Image rendering from line drawings is vital in design and image generation technologies reduce costs, yet professional line drawings demand preserving complex details. Text prompts…

cs.CV2023

DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model

Yichen Peng, Chunqi Zhao, Haoran Xie +2

Synthesizing face images from monochrome sketches is one of the most fundamental tasks in the field of image-to-image translation. However, it is still challenging to (1)~make mode…

cs.HC2021

SketchMeHow: Interactive Projection Guided Task Instruction with User Sketches

Haoran Xie, Yichen Peng, Hange Wang +1

In this work, we propose an interactive general instruction framework SketchMeHow to guidance the common users to complete the daily tasks in real-time. In contrast to the conventi…

cs.HC2026

Sensing Your Vocals: Exploring the Activity of Vocal Cord Muscles for Pitch Assessment Using Electromyography and Ultrasonography

Kanyu Chen, Rebecca Panskus, Erwin Wu +9

Vocal training is difficult because the muscles that control pitch, resonance, and phonation are internal and invisible to learners. This paper investigates how Electromyography (E…

cs.CV2022

BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis

Haiyang Liu, Zihao Zhu, Naoya Iwamoto +5

Achieving realistic, vivid, and human-like synthesized conversational gestures conditioned on multi-modal data is still an unsolved problem due to the lack of available datasets, m…

cs.CV2026

InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation

Yichen Peng, Jyun-Ting Song, Chen-Chieh Liao +3

Human-pet interaction estimation and generation remain underexplored due to the absence of a high-quality large-scale dataset. We present InterPet4D, the first multimodal dataset c…

cs.CV2024

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

Haiyang Liu, Zihao Zhu, Giorgio Becherini +7

We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements. To achieve this, we…

cs.CV2024

FilterPrompt: A Simple yet Efficient Approach to Guide Image Appearance Transfer in Diffusion Models

Xi Wang, Yichen Peng, Heng Fang +4

In controllable generation tasks, flexibly manipulating the generated images to attain a desired appearance or structure based on a single input image cue remains a critical and lo…

cs.GR2022

DualMotion: Global-to-Local Casual Motion Design for Character Animations

Yichen Peng, Chunqi Zhao, Haoran Xie +3

Animating 3D characters using motion capture data requires basic expertise and manual labor. To support the creativity of animation design and make it easier for common users, we p…

cs.GR2021

dualFace:Two-Stage Drawing Guidance for Freehand Portrait Sketching

Zhengyu Huang, Yichen Peng, Tomohiro Hibino +4

In this paper, we propose dualFace, a portrait drawing interface to assist users with different levels of drawing skills to complete recognizable and authentic face sketches. dualF…

cs.CV2025

SimDiff: Simulator-constrained Diffusion Model for Physically Plausible Motion Generation

Akihisa Watanabe, Jiawei Ren, Li Siyao +3

Generating physically plausible human motion is crucial for applications such as character animation and virtual reality. Existing approaches often incorporate a simulator-based mo…