Zhen Xu

17

Papers

45

Total Citations

Papers (17)

EnvGS: Modeling View-Dependent Appearance with Environment Gaussian

FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction

Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model

NeurIPS 2016arXiv

StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models

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

ERNet: Efficient Non-Rigid Registration Network for Point Sequences

Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction

Relightable and Animatable Neural Avatar from Sparse-View Video

4K4D: Real-Time 4D View Synthesis at 4K Resolution

Flow Contrastive Estimation of Energy-Based Models

360-Attack: Distortion-Aware Perturbations From Perspective-Views

Confidence Propagation Cluster: Unleash Full Potential of Object Detectors

Text-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation

Blemish-Aware and Progressive Face Retouching With Limited Paired Data

Learning Neural Volumetric Representations of Dynamic Humans in Minutes

Activity Auto-Completion: Predicting Human Activities From Partial Videos

Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding