Xuan Wang

34

Papers

45

Total Citations

Papers (34)

DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera

3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations

AniMo: Species-Aware Model for Text-Driven Animal Motion Generation

A3: Few-shot Prompt Learning of Unlearnable Examples with Cross-Modal Adversarial Feature Alignment

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

Diffusion-based Realistic Listening Head Generation via Hybrid Motion Modeling

A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields

Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring

FENeRF: Face Editing in Neural Radiance Fields

Hallucinated Neural Radiance Fields in the Wild

Deblur-NeRF: Neural Radiance Fields From Blurry Images

HDR-NeRF: High Dynamic Range Neural Radiance Fields

3D GAN Inversion With Facial Symmetry Prior

High-Fidelity Clothed Avatar Reconstruction From a Single Image

High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors

Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars

SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields

Local Implicit Ray Function for Generalizable Radiance Field Representation

UV Volumes for Real-Time Rendering of Editable Free-View Human Performance

On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos

FSI: Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras

GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

ToonTalker: Cross-Domain Face Reenactment

StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN

AvatarArtist: Open-Domain 4D Avatarization

HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars

Adaptive Learning of High-Value Regions for Semi-Supervised Medical Image Segmentation

Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking Heads

Fine-Grained 3D Gaussian Head Avatars Modeling from Static Captures via Joint Reconstruction and Registration

Images as Noisy Labels: Unleashing the Potential of the Diffusion Model for Open-Vocabulary Semantic Segmentation