Xiaoguang Han

55

Papers

106

Total Citations

Papers (55)

MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures

TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation

HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained Images

Towards Realistic Example-based Modeling via 3D Gaussian Stitching

Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence

Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On

Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion

Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement

A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Images

Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image

FPConv: Learning Local Flattening for Point Convolution

RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

Refer-It-in-RGBD: A Bottom-Up Approach for 3D Visual Grounding in RGBD Images

3DCaricShop: A Dataset and a Baseline Method for Single-View 3D Caricature Face Reconstruction

ETHSeg: An Amodel Instance Segmentation Network and a Real-World Dataset for X-Ray Waste Inspection

Revisiting Temporal Alignment for Video Restoration

Expressive Talking Head Generation With Granular Audio-Visual Control

Registering Explicit to Implicit: Towards High-Fidelity Garment Mesh Reconstruction From Single Images

Compound Domain Generalization via Meta-Knowledge Encoding

SharpContour: A Contour-Based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation

DArch: Dental Arch Prior-Assisted 3D Tooth Instance Segmentation With Weak Annotations

HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling

Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation

NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer

RaBit: Parametric Modeling of 3D Biped Cartoon Characters With a Topological-Consistent Dataset

NerVE: Neural Volumetric Edges for Parametric Curve Extraction From Point Cloud

SCoDA: Domain Adaptive Shape Completion for Real Scans

Learning 3D Scene Priors With 2D Supervision

MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling With Informative-Preserved Reconstruction and Self-Distilled Consistency

MVImgNet: A Large-Scale Dataset of Multi-View Images

REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos

High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference

HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation

Deep Mesh Reconstruction From Single RGB Images via Topology Modification Networks

LapsCore: Language-Guided Person Search via Color Reasoning

Preservational Learning Improves Self-Supervised Medical Image Models by Reconstructing Diverse Contexts

Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model Using Pixel-Aligned Reconstruction Priors

Activate and Reject: Towards Safe Domain Generalization under Category Shift

Efficient View Synthesis with Neural Radiance Distribution Field

Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images

Peeking into occluded joints: A novel framework for crowd pose estimation

Towards High-Fidelity Single-View Holistic Reconstruction of Indoor Scenes

TO-Scene: A Large-Scale Dataset for Understanding 3D Tabletop Scenes

Pose2Room: Understanding 3D Scenes from Human Activities

ME-PCN: Point Completion Conditioned on Mask Emptiness

Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture

Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D

IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images

LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset

PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns

Deep Reinforcement Learning of Volume-Guided Progressive View Inpainting for 3D Point Scene Completion From a Single Depth Image

Skeleton-bridged Point Completion: From Global Inference to Local Adjustment

CODA: Generalizing to Open and Unseen Domains with Compaction and Disambiguation

A Comprehensive Benchmark for Neural Human Radiance Fields