activity
20142024
most citedThe DiffuseStyleGesture+ entry to the GENEA Challenge 2023

31 citations · 63 across the 16 of their papers we have counts for

collaborators

16 papers

cs.CV2024

TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling

Dong Huo, Zixin Guo, Xinxin Zuo +6

Given a 3D mesh, we aim to synthesize 3D textures that correspond to arbitrary textual descriptions. Current methods for generating and assembling textures from sampled views often…

cs.CV2024

EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head

Qianyun He, Xinya Ji, Yicheng Gong +11

We present a novel approach for synthesizing 3D talking heads with controllable emotion, featuring enhanced lip synchronization and rendering quality. Despite significant progress…

cs.CV2024

AutoTVG: A New Vision-language Pre-training Paradigm for Temporal Video Grounding

Xing Zhang, Jiaxi Gu, Haoyu Zhao +6

Temporal Video Grounding (TVG) aims to localize a moment from an untrimmed video given the language description. Since the annotation of TVG is labor-intensive, TVG under limited s…

cs.CV20241 cited

Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model

Xu He, Qiaochu Huang, Zhensong Zhang +7

Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural hum…

eess.IV2024

Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution

Qingping Zheng, Ling Zheng, Yuanfan Guo +4

Artifact-free super-resolution (SR) aims to translate low-resolution images into their high-resolution counterparts with a strict integrity of the original content, eliminating any…

cs.CV2024

LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model

Runhui Huang, Kaixin Cai, Jianhua Han +6

Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provi…